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

    Neuronpedia

    INDEX
    Explanations

    equip people with skills

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    t
    1.58
    g
    1.25
    ли
    1.14
    ہ
    1.12
    на
    1.05
    ла
    1.05
    ci
    0.95
    gambar
    0.94
    ą
    0.92
    dari
    0.88
    POSITIVE LOGITS
     can
    1.49
    ד
    1.32
     you
    1.13
     an
    1.13
    il
    1.13
    T
    1.12
    로
    1.07
    ל
    1.05
    ما
    1.00
    也
    0.98
    Act Density 0.001%

    No Known Activations