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

    Neuronpedia

    INDEX
    Explanations

    button or click

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    صح
    0.68
    layered
    0.63
    Meine
    0.59
    Giải
    0.58
    淬
    0.57
     impeccable
    0.57
     полага
    0.57
    Script
    0.56
    חד
    0.56
    dy
    0.55
    POSITIVE LOGITS
    按钮
    0.85
     atau
    0.82
     क्लिक
    0.81
     یا
    0.78
     botão
    0.78
     किंवा
    0.75
    をクリック
    0.74
     लिंक
    0.74
     botón
    0.74
    เพื่อ
    0.72
    Act Density 0.001%

    No Known Activations