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

    Neuronpedia

    INDEX
    Explanations

    symbols and notation used in mathematical equations and formal proofs

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

    Mathematical or logical expressions

    np_acts-logits-general · gemini-2.0-flash

    mathematical and code structures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    geord
    -0.46
     Mr
    -0.45
    満
    -0.44
    gene
    -0.44
    сто
    -0.42
    /**
    -0.41
    Mr
    -0.41
     Lev
    -0.41
     le
    -0.40
     borer
    -0.40
    POSITIVE LOGITS
     فريبيس
    1.03
     $\
    0.92
    exitRule
    0.91
    fillType
    0.89
    adaptiveStyles
    0.86
    }{$\
    0.84
     Мексичка
    0.81
    ftagPool
    0.80
    ]),
    0.80
    principalColumn
    0.79
    Act Density 1.790%

    No Known Activations