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

    Neuronpedia

    INDEX
    Explanations

    compliant

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .SelectedIndexChanged
    -0.07
    ็กหญ
    -0.07
    え
    -0.06
    beth
    -0.06
    &E
    -0.06
    569
    -0.06
     drafting
    -0.06
     teamwork
    -0.06
    立ち
    -0.06
     row
    -0.06
    POSITIVE LOGITS
    лату
    0.07
    _NB
    0.07
     Fountain
    0.07
    vlc
    0.07
    /notification
    0.06
     tělo
    0.06
     */↵
    0.06
    _USERNAME
    0.06
    ského
    0.06
    δοση
    0.06
    Act Density 0.000%

    No Known Activations