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

    Neuronpedia

    INDEX
    Explanations

    hidden spaces

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Magnum
    -0.06
    _WARNING
    -0.06
     الأك
    -0.06
     приобрет
    -0.06
     المع
    -0.06
    .setItems
    -0.06
     OBS
    -0.06
    يفة
    -0.06
    banana
    -0.06
     μεταξύ
    -0.06
    POSITIVE LOGITS
    LV
    0.07
     State
    0.07
    arily
    0.06
     Xxx
    0.06
     
    0.06
    ollow
    0.06
    .pic
    0.06
     liberals
    0.06
    raph
    0.06
     senate
    0.06
    Act Density 0.088%

    No Known Activations