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

    Neuronpedia

    INDEX
    Explanations

    char

    np_max-act · gemini-2.0-flash

    The neuron responds to occurrences of the C type keyword “char” in code, i.e. it fires on char‐based declarations.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Boo
    -0.07
    袖
    -0.07
    ampoo
    -0.07
     تهیه
    -0.07
     diffé
    -0.07
    ีต
    -0.07
    Inverse
    -0.06
     Incontri
    -0.06
    .aspx
    -0.06
    nect
    -0.06
    POSITIVE LOGITS
    (char
    0.10
    	char
    0.09
     char
    0.08
    (Char
    0.07
    _CHAR
    0.07
     реб
    0.07
    chars
    0.07
    AR
    0.07
     Sara
    0.06
     SAR
    0.06
    Act Density 0.007%

    No Known Activations