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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     pulmonary
    -0.07
    /ref
    -0.06
    (xhr
    -0.06
    iddy
    -0.06
     поверх
    -0.06
     Jay
    -0.06
    üven
    -0.06
     executives
    -0.06
     기록
    -0.06
    @AllArgsConstructor
    -0.06
    POSITIVE LOGITS
    Scaling
    0.07
    553
    0.07
     šk
    0.06
    |h
    0.06
     ever
    0.06
     كبير
    0.06
    _scaled
    0.06
    tolist
    0.06
    190
    0.06
    ONGLONG
    0.06
    Act Density 0.003%

    No Known Activations