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

    Neuronpedia

    INDEX
    Explanations

    growth

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ruth
    -0.09
     electoral
    -0.08
     గా
    -0.07
    身份
    -0.07
    cljs
    -0.07
    klass
    -0.07
    енности
    -0.07
    played
    -0.07
    ৰি
    -0.07
     ಕಾಲ
    -0.07
    POSITIVE LOGITS
     sap
    0.08
     unchecked
    0.08
     prospects
    0.08
     ży
    0.07
     Hugh
    0.07
    过程中
    0.07
     spur
    0.07
     protr
    0.07
     Kit
    0.07
     prosper
    0.07
    Act Density 0.012%

    No Known Activations