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

    Neuronpedia

    INDEX
    Explanations

    translate languages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    こと
    0.44
    _
    0.43
     visage
    0.43
    liches
    0.42
     impure
    0.40
    MainWindow
    0.40
    oring
    0.39
    gged
    0.39
    curs
    0.39
     إن
    0.39
    POSITIVE LOGITS
    စ
    0.55
    ześnie
    0.50
    波動方程式
    0.49
     pembelajaran
    0.48
     Byl
    0.48
    辊
    0.48
    گیری
    0.48
     Substitution
    0.47
     //-->
    0.47
     nytt
    0.46
    Act Density 0.002%

    No Known Activations