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

    Neuronpedia

    INDEX
    Explanations

    processor

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Evrop
    -0.07
     yên
    -0.06
    局
    -0.06
    /dashboard
    -0.06
     steal
    -0.06
     треба
    -0.06
    사는
    -0.06
    _MINUS
    -0.06
    Mixin
    -0.06
    药
    -0.06
    POSITIVE LOGITS
     accredited
    0.07
    \Config
    0.07
     Pradesh
    0.07
     saf
    0.07
     admin
    0.06
    resden
    0.06
     triple
    0.06
    .Amount
    0.06
    _product
    0.06
    $smarty
    0.06
    Act Density 0.003%

    No Known Activations