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

    Neuronpedia

    INDEX
    Explanations

    sense

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    َك
    -0.07
    ота
    -0.07
     mActivity
    -0.06
     бан
    -0.06
     الس
    -0.06
    picked
    -0.06
    _HIT
    -0.06
    UX
    -0.06
     marriages
    -0.06
     فوت
    -0.06
    POSITIVE LOGITS
    /react
    0.07
    ="\
    0.06
     athlete
    0.06
     squeezed
    0.06
     Μη
    0.06
     '\
    0.06
     德
    0.06
     bool
    0.06
    妇
    0.06
    amaha
    0.06
    Act Density 0.000%

    No Known Activations