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

    Neuronpedia

    INDEX
    Explanations

    hierarchical, Dane, develops, Germanic, folklore

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     품질
    0.50
    撅
    0.47
    供应链
    0.46
     فلسطینی
    0.45
    买了
    0.44
    뒀
    0.44
    镟
    0.43
     Trudy
    0.43
    indentLevel
    0.43
    0.42
    POSITIVE LOGITS
    AC
    0.39
    嗜
    0.38
    sense
    0.38
    min
    0.38
     etc
    0.37
    short
    0.36
    )(\
    0.36
    વાલ
    0.36
     sorted
    0.36
     baar
    0.35
    Act Density 0.000%

    No Known Activations