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

    Neuronpedia

    INDEX
    Explanations

    numbers, lists, Python code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    通风
    0.48
    राबरी
    0.48
     frapp
    0.47
     gonad
    0.47
    d
    0.47
     hamper
    0.46
     terang
    0.46
    s
    0.46
    ড়ায়
    0.46
     kuu
    0.46
    POSITIVE LOGITS
    ने
    0.59
     on
    0.55
    મ
    0.55
    з
    0.54
    _
    0.53
    ме
    0.52
    िंग
    0.50
    ле
    0.50
    скую
    0.49
     shri
    0.49
    Act Density 0.033%

    No Known Activations