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

    Neuronpedia

    INDEX
    Explanations

    Universities and colleges

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ﯹ
    -0.07
    .raise
    -0.07
    ivre
    -0.07
     harga
    -0.07
    idders
    -0.07
     כולו
    -0.07
    ro
    -0.07
    �
    -0.07
    .tr
    -0.07
    믕
    -0.07
    POSITIVE LOGITS
     PAY
    0.08
     enum
    0.07
     connects
    0.07
     Feed
    0.07
    不代表
    0.07
    routes
    0.07
     мат
    0.07
     incent
    0.06
     unequal
    0.06
     Sac
    0.06
    Act Density 0.079%

    No Known Activations