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

    Neuronpedia

    INDEX
    Explanations

    code and software

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    maj
    -0.07
     науч
    -0.07
     Zu
    -0.06
     آنان
    -0.06
    梅
    -0.06
     giochi
    -0.06
     gameId
    -0.06
     Consort
    -0.06
     dabei
    -0.06
     Ange
    -0.06
    POSITIVE LOGITS
     KEY
    0.07
    682
    0.07
    风
    0.07
    ButtonText
    0.07
    Surv
    0.07
    687
    0.07
    Número
    0.06
    OutOf
    0.06
    overnment
    0.06
    异
    0.06
    Act Density 0.000%

    No Known Activations