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

    Neuronpedia

    INDEX
    Explanations

    bust size and fiber intake

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    has
    0.40
    control
    0.39
    Span
    0.39
    공
    0.38
     favorit
    0.38
     خوف
    0.38
     공
    0.37
    controlling
    0.37
    Control
    0.36
     방식으로
    0.35
    POSITIVE LOGITS
     المؤس
    0.46
     Bxb
    0.45
    ဋ
    0.41
     插
    0.40
     учре
    0.40
    㓩
    0.40
    dade
    0.39
     Elemente
    0.39
     Produkte
    0.39
     ক্যারি
    0.39
    Act Density 0.001%

    No Known Activations