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

    Neuronpedia

    INDEX
    Explanations

    use

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     الشخص
    -0.06
     пом
    -0.06
    urgical
    -0.06
     боли
    -0.06
     QC
    -0.05
    Conexion
    -0.05
    IBM
    -0.05
    واز
    -0.05
    .signup
    -0.05
    ける
    -0.05
    POSITIVE LOGITS
    koliv
    0.07
    Highlights
    0.07
    undai
    0.06
     Underground
    0.06
    tier
    0.06
    _TEAM
    0.06
     GetValue
    0.06
    uhe
    0.06
     mehr
    0.06
     Observer
    0.06
    Act Density 0.011%

    No Known Activations