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

    Neuronpedia

    INDEX
    Explanations

    clicking button

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     चाहर
    0.42
    DETAIL
    0.41
     عوامل
    0.40
    ும
    0.40
    สร
    0.39
    pref
    0.39
     évaluations
    0.39
    CHARACTER
    0.39
     fattori
    0.39
     EXEMPLARY
    0.39
    POSITIVE LOGITS
    按钮
    0.78
     button
    0.77
     toggle
    0.77
     Toggle
    0.70
     botón
    0.68
    ボタン
    0.65
     Button
    0.64
     버튼
    0.64
     кноп
    0.63
     comando
    0.63
    Act Density 0.137%

    No Known Activations