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

    Neuronpedia

    INDEX
    Explanations

    people who collect

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ser
    0.81
    a
    0.75
    이면
    0.73
    ीत
    0.72
    йся
    0.71
    son
    0.69
     Grü
    0.68
    ss
    0.68
     undersigned
    0.68
     Architecture
    0.66
    POSITIVE LOGITS
    𝘶
    0.93
    го
    0.91
    バトル
    0.81
    อย่าง
    0.80
    们
    0.80
    という
    0.79
    ുകൾ
    0.79
    ുകളും
    0.79
    ما
    0.79
     musculaire
    0.78
    Act Density 0.000%

    No Known Activations