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

    Neuronpedia

    INDEX
    Explanations

    detects range and targets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    قي
    0.52
    asch
    0.48
    kich
    0.48
    เลี้ยง
    0.48
    키
    0.48
    )，
    0.47
    剂
    0.46
     RB
    0.46
     +"
    0.45
    ENTER
    0.45
    POSITIVE LOGITS
     নৌ
    0.57
    ரின்
    0.52
     තම
    0.52
    '
    0.52
     сверху
    0.52
     pequena
    0.51
     کشتی
    0.50
    arın
    0.50
    หรือไม่
    0.49
     Bakan
    0.49
    Act Density 0.002%

    No Known Activations