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

    Neuronpedia

    INDEX
    Explanations

    range or sequence

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ır
    1.06
    ava
    1.02
    alto
    0.93
    ave
    0.93
    alar
    0.93
    agregar
    0.91
    ai
    0.91
    aka
    0.90
    fö
    0.90
    Interfaz
    0.89
    POSITIVE LOGITS
    ารย์
    0.93
     יו
    0.92
     وعلى
    0.89
     نسخة
    0.88
     lhe
    0.87
     ณ
    0.86
     खेली
    0.84
    חנו
    0.82
     Convertible
    0.82
     Thereafter
    0.79
    Act Density 0.000%

    No Known Activations