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

    Neuronpedia

    INDEX
    Explanations

    Daily business update

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ب
    0.50
    ສ່ວນ
    0.46
    부
    0.44
    кой
    0.43
    в
    0.42
    إذا
    0.42
     dwelt
    0.40
    텅
    0.39
     bunting
    0.39
    ב
    0.39
    POSITIVE LOGITS
    stuffs
    0.54
    ilon
    0.52
     хі
    0.52
    3
    0.52
     ಗಳ
    0.51
    il
    0.49
    ümü
    0.49
    nut
    0.48
    ata
    0.48
    ivi
    0.48
    Act Density 0.000%

    No Known Activations