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

    Neuronpedia

    INDEX
    Explanations

    asking for requests

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    р
    1.10
    र
    0.91
    ే
    0.90
    ش
    0.75
    на
    0.75
    0.72
    ル
    0.71
     weekends
    0.71
    ку
    0.71
    рки
    0.70
    POSITIVE LOGITS
    𝙚
    0.82
    𝙢
    0.74
    ination
    0.69
    ishly
    0.68
    HCR
    0.68
    mselves
    0.68
    jší
    0.68
    :‏
    0.68
    𝙙
    0.67
    𝙜
    0.67
    Act Density 0.013%

    No Known Activations