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

    Neuronpedia

    INDEX
    Explanations

    offering help for sensitive topics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Balance
    0.66
     balance
    0.66
    balance
    0.62
    Balance
    0.61
    參數
    0.61
    ple
    0.59
    平衡
    0.58
    ܩ
    0.58
    acti
    0.57
     parameters
    0.56
    POSITIVE LOGITS
     капита
    0.71
    ジュール
    0.62
    jot
    0.62
    xi
    0.62
     Xanth
    0.62
    xanth
    0.61
    btn
    0.61
     ஸ்ரீ
    0.60
    R
    0.60
    ಿಗಳ
    0.60
    Act Density 0.087%

    No Known Activations