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

    Neuronpedia

    INDEX
    Explanations

    life and shadow

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ب
    1.07
     лиц
    1.02
    别的
    0.96
     сотрудников
    0.89
     лица
    0.88
    ટ્સ
    0.83
    هم
    0.82
    с
    0.81
    ك
    0.81
     в
    0.80
    POSITIVE LOGITS
     calorimeter
    1.05
     esophagus
    1.04
     bitterly
    1.01
     fratt
    1.01
    কেট
    1.01
     territoire
    1.00
     gaan
    0.98
     starter
    0.96
     intervalo
    0.94
     wahr
    0.93
    Act Density 0.009%

    No Known Activations