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

    Neuronpedia

    INDEX
    Explanations

    phonetic transcriptions and linguistic terms related to phonology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Characters followed by special punctuation or diacritics

    np_acts-logits-general · gemini-2.0-flash

    linguistic structures, languages, or cases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    .}\
    -0.51
    }));
    -0.50
     }}}{
    -0.48
    eren
    -0.48
    .)}
    -0.47
    isEqualTo
    -0.47
    دانشنامهٔ
    -0.46
     issue
    -0.46
    !")
    -0.46
     Exp
    -0.46
    POSITIVE LOGITS
     betweenstory
    0.84
     marquées
    0.69
     Rhymes
    0.68
    adə
    0.66
     étoit
    0.66
     avoient
    0.65
    ThroughAttribute
    0.65
     Herodotus
    0.64
     Semantics
    0.63
     fédé
    0.63
    Act Density 0.172%

    No Known Activations