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

    Neuronpedia

    INDEX
    Explanations

    Alphanumeric characters

    np_max-act · gemini-2.0-flash

    identifiers and keys used in programming or data structures, especially in relation to character encoding.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    This neuron activates on hexadecimal‐style Unicode code‐point escapes and range specifications (e.g. the “\uXXXX”/“\xXX–\xYY” pieces).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    �
    -0.08
     ABI
    -0.07
     Mai
    -0.06
    	result
    -0.06
     tex
    -0.06
     GAP
    -0.06
    Repo
    -0.06
     shar
    -0.06
     湖
    -0.06
     والس
    -0.06
    POSITIVE LOGITS
    -bar
    0.06
    变得
    0.06
     tutorials
    0.06
    �
    0.06
    铺
    0.06
     regimes
    0.06
    SSL
    0.06
    ác
    0.06
    Buying
    0.06
     рядом
    0.06
    Act Density 0.005%

    No Known Activations