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

    Neuronpedia

    INDEX
    Explanations

    list items

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ​​
    0.76
    𝒶
    0.72
    dans
    0.71
    ़
    0.68
     peran
    0.67
    Ingredient
    0.66
    MainActivity
    0.65
    অর্থ
    0.65
    ि
    0.64
     личности
    0.64
    POSITIVE LOGITS
    ات
    0.81
    ت
    0.75
    iş
    0.65
    mselves
    0.64
    داران
    0.64
    ない
    0.63
    கள்
    0.63
     सिलसिला
    0.63
    ➞
    0.62
    री
    0.61
    Act Density 0.023%

    No Known Activations