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

    Neuronpedia

    INDEX
    Explanations

    ,

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     cultural
    -0.07
     encompasses
    -0.06
     closes
    -0.06
     Sciences
    -0.06
     zev
    -0.06
     своих
    -0.06
     basics
    -0.06
     Ras
    -0.06
    asses
    -0.06
     astounding
    -0.06
    POSITIVE LOGITS
    _json
    0.06
    monton
    0.06
    production
    0.06
     sécurité
    0.06
     polym
    0.06
     tổn
    0.06
    ساب
    0.06
    )+
    0.06
    owment
    0.06
    elu
    0.06
    Act Density 0.000%

    No Known Activations