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

    Neuronpedia

    INDEX
    Explanations

    userData structure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    تس
    0.79
    ल
    0.77
    ти
    0.76
    الات
    0.75
    Вер
    0.74
    کش
    0.73
    ли
    0.71
    ות
    0.71
    га
    0.70
    ला
    0.70
    POSITIVE LOGITS
     Kanye
    1.02
     LEED
    0.98
     Marian
    0.98
     shunt
    0.93
     IPCC
    0.93
     colaborar
    0.92
     FIFA
    0.92
     Westminster
    0.91
     ODM
    0.91
     rapper
    0.91
    Act Density 0.000%

    No Known Activations