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

    Neuronpedia

    INDEX
    Explanations

    quadratic equation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    фор
    2.13
     hề
    2.02
    và
    1.82
    ве
    1.80
    쐞
    1.78
     paling
    1.72
    癀
    1.69
    ต์
    1.67
    𝙜
    1.67
    鸰
    1.67
    POSITIVE LOGITS
    TER
    2.14
    IAN
    2.11
    t
    2.02
    ます
    1.90
    ਾ
    1.85
    ARE
    1.84
    szer
    1.76
    TS
    1.74
    ية
    1.73
    ী
    1.73
    Act Density 0.017%

    No Known Activations