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

    Neuronpedia

    INDEX
    Explanations

    sentences or phrases containing significant medical cautions or instructions

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

    place for

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    richTextPanel
    -0.72
     Roskov
    -0.68
    principalTable
    -0.66
    UnsafeEnabled
    -0.66
     فريبيس
    -0.63
    ArgsConstructor
    -0.63
     informée
    -0.63
    IUrlHelper
    -0.62
    parsedMessage
    -0.62
    StoreMessageInfo
    -0.61
    POSITIVE LOGITS
     Dead
    0.38
     personalizadas
    0.37
    <eos>
    0.37
     personalizados
    0.35
     douce
    0.35
     Again
    0.34
     Gre
    0.33
    DEC
    0.32
    dec
    0.32
    Dec
    0.32
    Act Density 0.013%

    No Known Activations