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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions and symbols that indicate complex operations or functions

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

    Mathematical or logical expressions with parentheses and symbols

    np_acts-logits-general · gemini-2.0-flash

    logic or code expressions following punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    RESUMEN
    -0.45
    }{*}{}
    -0.44
     herself
    -0.42
    onShow
    -0.41
    fuß
    -0.40
    herself
    -0.40
     listrik
    -0.39
    Carrière
    -0.39
    Życiorys
    -0.39
     imageNamed
    -0.39
    POSITIVE LOGITS
    ",(
    0.84
    [(
    0.82
    }{(
    0.81
    =((
    0.79
    ((
    0.78
    >((
    0.78
    }}{(
    0.77
    (((
    0.76
    )((
    0.76
    *((
    0.75
    Act Density 1.260%

    No Known Activations