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

    Neuronpedia

    INDEX
    Explanations

    references to collections of stories or anthologies

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

    Punctuation (.,;) and conjunctions (but, And)

    np_acts-logits-general · gemini-2.0-flash

    multiple selections and variety

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    EDEFAULT
    -0.72
    dataclass
    -0.64
    SharedDtor
    -0.61
    yyj
    -0.59
    flashdata
    -0.58
     ddelweddau
    -0.57
    enumii
    -0.57
     nargin
    -0.56
    libft
    -0.55
     فريبيس
    -0.54
    POSITIVE LOGITS
     ranging
    0.80
     includes
    0.76
     mostly
    0.73
    どれも
    0.73
    ranging
    0.72
     some
    0.68
    mostly
    0.67
     selections
    0.67
     mayoría
    0.65
     Includes
    0.65
    Act Density 0.398%

    No Known Activations