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

    Neuronpedia

    INDEX
    Explanations

    asking to share

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ea
    3.15
    ៉
    2.97
    eo
    2.72
    ej
    2.61
    fasst
    2.48
    ी
    2.48
    lard
    2.47
    e
    2.47
    lardan
    2.47
    larda
    2.46
    POSITIVE LOGITS
    ̩
    2.77
    お得
    2.72
    SeekBar
    2.69
    おしゃれ
    2.52
    お知らせ
    2.40
    V
    2.37
    PS
    2.36
    P
    2.32
    ंचे
    2.32
    ح
    2.31
    Act Density 1.340%

    No Known Activations