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

    Neuronpedia

    INDEX
    Explanations

    there

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -rule
    -0.07
    NCY
    -0.07
    ())),
    -0.07
    álním
    -0.06
     played
    -0.06
    preci
    -0.06
    bsd
    -0.06
     خی
    -0.06
    ility
    -0.06
     кирп
    -0.06
    POSITIVE LOGITS
     condol
    0.07
    .Err
    0.06
    _KeyPress
    0.06
     مشخص
    0.06
     removes
    0.06
    �
    0.06
     prize
    0.06
     traces
    0.06
     ανα
    0.06
     implanted
    0.06
    Act Density 0.000%

    No Known Activations