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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    angs
    -0.08
     væ
    -0.07
    incorrect
    -0.07
    _from
    -0.07
    	using
    -0.06
    oğunluk
    -0.06
    یف
    -0.06
    _rows
    -0.06
    mousedown
    -0.06
    ysts
    -0.06
    POSITIVE LOGITS
     Аф
    0.07
    گي
    0.06
     الكه
    0.06
    Virgin
    0.06
     lạ
    0.06
     عرب
    0.06
    .barDockControl
    0.06
     Virgin
    0.06
    =c
    0.06
     ark
    0.06
    Act Density 0.024%

    No Known Activations