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

    Neuronpedia

    INDEX
    Explanations

    times and urls

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ก
    0.66
    த்தில்
    0.63
    ↵
    0.62
    ט
    0.61
    지
    0.60
    ção
    0.59
    it
    0.55
    ون
    0.55
    ิน
    0.55
    이었다
    0.55
    POSITIVE LOGITS
     乀
    0.50
    AttrName
    0.50
     robbery
    0.48
    してます
    0.47
     hồ
    0.46
     よる
    0.46
     tại
    0.43
     atrium
    0.43
     blunder
    0.43
     thép
    0.42
    Act Density 0.000%

    No Known Activations