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

    Neuronpedia

    INDEX
    Explanations

    真好

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     তথাপি
    0.82
     chau
    0.74
     innovations
    0.74
     proportion
    0.73
    colnames
    0.73
    ಿಗಳು
    0.72
     thay
    0.71
    er
    0.71
    ance
    0.71
    flo
    0.71
    POSITIVE LOGITS
    rnd
    0.79
    珏
    0.77
    يع
    0.75
    ሁሉም
    0.75
    𓏸
    0.75
    香り
    0.74
    ށ
    0.74
    邑
    0.73
    🏃
    0.72
    🩹
    0.71
    Act Density 0.004%

    No Known Activations