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

    Neuronpedia

    INDEX
    Explanations

    database and file storage

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     обре
    1.66
     foremost
    1.61
    пу
    1.61
    ᴠ
    1.56
    Ví
    1.55
     decent
    1.55
     afford
    1.54
    atory
    1.52
     aspetto
    1.51
    ated
    1.50
    POSITIVE LOGITS
    zelfde
    2.18
    ت
    2.13
    ن
    1.99
    การ
    1.92
    дження
    1.92
    お
    1.90
    ্র
    1.88
    স
    1.86
    ளும்
    1.85
    1.80
    Act Density 0.084%

    No Known Activations