Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    consonant

    np_max-act · gemini-2.0-flash

    This neuron detects mentions of consonants (e.g. “consonant,” “consonant cluster,” etc.) in phonetic/phonological discussion.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8

    phonetic features and structures of constructed languages.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     humano
    -0.07
     marking
    -0.07
     sms
    -0.07
     projection
    -0.06
     foss
    -0.06
     tube
    -0.06
    ampus
    -0.06
     articulated
    -0.06
     predicate
    -0.06
    Technical
    -0.06
    POSITIVE LOGITS
     conson
    0.07
     войны
    0.07
     carbs
    0.06
     قهر
    0.06
     Cena
    0.06
    aty
    0.06
     kami
    0.06
    AndUpdate
    0.06
    liable
    0.06
     //================================================================
    0.06
    Act Density 0.001%

    No Known Activations