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

    Neuronpedia

    INDEX
    Explanations

    Markdown

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     incom
    0.38
     entrambi
    0.38
     bonuses
    0.36
     அல்லது
    0.35
     Every
    0.34
     convex
    0.33
     compartments
    0.33
     elabor
    0.33
     irrig
    0.33
     outpatient
    0.33
    POSITIVE LOGITS
    可知
    0.42
    ㈡
    0.39
    这段
    0.38
    ложение
    0.38
     evidentemente
    0.37
     అంటే
    0.37
     विदेश
    0.36
    рыя
    0.35
     رحمه
    0.35
     Бог
    0.35
    Act Density 0.181%

    No Known Activations