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

    Neuronpedia

    INDEX
    Explanations

    conditional statements and variations in reporting

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

    not entirely

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    FunctionFlags
    -0.43
    astify
    -0.42
    endpush
    -0.42
    acamata
    -0.41
    clés
    -0.41
    mybatisplus
    -0.41
    twimg
    -0.40
    MMS
    -0.39
    Edd
    -0.39
    اریخ
    -0.38
    POSITIVE LOGITS
     entirely
    0.50
     resourceCulture
    0.47
     completely
    0.45
    principalTable
    0.44
     altogether
    0.44
     zupełnie
    0.44
     outright
    0.44
     вовсе
    0.42
     Completely
    0.41
     ogóle
    0.41
    Act Density 0.263%

    No Known Activations