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

    Neuronpedia

    INDEX
    Explanations

    wonder and ponder

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     corrientes
    1.94
    fst
    1.91
    ILL
    1.77
    鳃
    1.77
    ಗೆ
    1.76
    いが
    1.70
    eru
    1.67
    want
    1.66
     compds
    1.66
     Đây
    1.65
    POSITIVE LOGITS
    ل
    3.14
    ০০
    2.94
    ہ
    2.45
    ící
    2.38
    ться
    2.36
    ной
    2.28
    ['
    2.25
    이자
    2.22
    在
    2.20
    ोतरी
    2.16
    Act Density 0.082%

    No Known Activations