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

    Neuronpedia

    INDEX
    Explanations

    specific terms or phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    䪱
    0.45
     없다
    0.43
     беремен
    0.43
    ption
    0.41
    眄
    0.40
     бере
    0.40
    cran
    0.40
     अधिकतर
    0.40
     جهد
    0.39
    שוט
    0.39
    POSITIVE LOGITS
    InfoWindow
    0.46
    С
    0.46
    omos
    0.46
    サ
    0.46
    감이
    0.44
    ところが
    0.43
    OMS
    0.43
    یف
    0.41
     Huss
    0.41
    Admin
    0.41
    Act Density 0.001%

    No Known Activations