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

    Neuronpedia

    INDEX
    Explanations

    store data

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    出
    0.59
    ادي
    0.55
    は
    0.54
    لي
    0.52
    는
    0.52
    程式
    0.52
    bringen
    0.52
    vé
    0.51
    開
    0.50
    ير
    0.50
    POSITIVE LOGITS
     저장
    0.79
     storage
    0.78
    ag
    0.77
     ذخ
    0.74
     almacenamiento
    0.73
     保存
    0.72
     disimpan
    0.71
    yl
    0.70
     storing
    0.70
    ai
    0.70
    Act Density 0.049%

    No Known Activations