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

    Neuronpedia

    INDEX
    Explanations

    return or coming back

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    lja
    0.91
    larni
    0.88
    l
    0.88
    j
    0.87
    ซ์
    0.87
    læ
    0.86
    ש
    0.84
     résulte
    0.84
    К
    0.84
     conç
    0.83
    POSITIVE LOGITS
    п
    0.73
    нні
    0.72
    ઓ
    0.72
    comers
    0.72
    ace
    0.70
    त
    0.70
    のか
    0.68
    处的
    0.66
    .\
    0.65
    そこ
    0.65
    Act Density 0.131%

    No Known Activations