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

    Neuronpedia

    INDEX
    Explanations

    quotations around words or phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    為
    0.74
    ⺆
    0.72
    ༌
    0.71
    ता
    0.71
     produ
    0.71
    𝙽
    0.71
    ContextCompat
    0.69
    为
    0.68
    Με
    0.67
    爲
    0.67
    POSITIVE LOGITS
    er
    1.23
    र
    1.13
    e
    1.13
    i
    1.12
    o
    1.08
    ed
    1.07
    ت
    1.07
    ی
    1.02
    هما
    1.01
    d
    0.99
    Act Density 0.243%

    No Known Activations