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

    Neuronpedia

    INDEX
    Explanations

    period

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    upos
    -0.07
     Stroke
    -0.07
    ա�
    -0.06
    %E
    -0.06
     Personnel
    -0.06
    ruž
    -0.06
    ropoda
    -0.06
    aoke
    -0.06
    koli
    -0.06
    ffiti
    -0.06
    POSITIVE LOGITS
    ocker
    0.07
     conduct
    0.07
    色
    0.06
    ые
    0.06
    forest
    0.06
    _download
    0.06
     во
    0.06
     فور
    0.06
     swallow
    0.06
    О
    0.06
    Act Density 0.003%

    No Known Activations