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

    Neuronpedia

    INDEX
    Explanations

    override string

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     centimeter
    1.16
    ន្ថ
    1.01
    ukkh
    1.01
     PAH
    0.98
    DVRIP
    0.98
    ار
    0.98
     ApJ
    0.98
    keme
    0.97
    dür
    0.96
    inak
    0.94
    POSITIVE LOGITS
    “
    0.89
    அ
    0.88
     γίνει
    0.87
    $(
    0.87
    （
    0.82
     ό
    0.81
    অ
    0.78
    Descripción
    0.77
    1
    0.75
     মধ্যে
    0.74
    Act Density 0.000%

    No Known Activations