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

    Neuronpedia

    INDEX
    Explanations

    expansion, scope

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    education
    -0.06
    วน
    -0.06
     tox
    -0.06
     Pow
    -0.06
     impe
    -0.06
    234
    -0.06
     prick
    -0.06
    949
    -0.06
     high
    -0.06
     drastically
    -0.06
    POSITIVE LOGITS
     Machinery
    0.07
     fantast
    0.06
     sharedPreferences
    0.06
    _canvas
    0.06
    онах
    0.06
    ($)
    0.06
     ráno
    0.06
     göre
    0.06
     المغرب
    0.06
     Liberal
    0.06
    Act Density 0.055%

    No Known Activations