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

    Neuronpedia

    INDEX
    Explanations

    pronunciation guides

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     necessidades
    0.94
     gotta
    0.88
     interchangeable
    0.88
    Bike
    0.88
     другим
    0.86
    vedi
    0.84
     необходимости
    0.84
    ────────────────
    0.83
     other
    0.83
    Catalog
    0.83
    POSITIVE LOGITS
     وم
    1.20
    óa
    1.16
     तथा
    1.16
     وأ
    1.11
    和
    1.05
     pejabat
    1.05
    osecond
    1.04
    σο
    1.04
     ומ
    1.03
    ছেন
    1.03
    Act Density 0.273%

    No Known Activations