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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .row
    -0.07
     ALLOW
    -0.06
    provide
    -0.06
    GTK
    -0.06
     complying
    -0.06
     airborne
    -0.06
    ysical
    -0.06
    _bed
    -0.06
    stead
    -0.06
     "$
    -0.06
    POSITIVE LOGITS
    用品
    0.07
    腿
    0.07
     пару
    0.07
     taşıy
    0.07
    (egt
    0.06
    (月
    0.06
     вихов
    0.06
    838
    0.06
     piger
    0.06
     použit
    0.06
    Act Density 0.204%

    No Known Activations