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

    Neuronpedia

    INDEX
    Explanations

    references to variable types or values in code documentation

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

    value followed by punctuation or code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     of
    -0.35
    if
    -0.32
     av
    -0.32
     dă
    -0.32
    wijs
    -0.32
    0
    -0.31
     controllare
    -0.31
     Far
    -0.31
    St
    -0.31
    WebMethod
    -0.30
    POSITIVE LOGITS
     autorytatywna
    0.76
     Value
    0.74
     שוליים
    0.72
    exitRule
    0.66
     VALUE
    0.66
     Obrador
    0.62
    Value
    0.61
    VALUE
    0.58
     getValue
    0.56
     صوتيه
    0.56
    Act Density 0.034%

    No Known Activations