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

    Neuronpedia

    INDEX
    Explanations

    negate, refuse, skip

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     nicht
    0.49
    s
    0.48
     ikke
    0.47
     doesn
    0.47
    3
    0.46
    หลาย
    0.46
     unable
    0.46
     אין
    0.44
    ไม่
    0.44
     not
    0.43
    POSITIVE LOGITS
     nor
    0.87
     sondern
    0.69
     veya
    0.64
     niti
    0.64
     tampoco
    0.63
    而是
    0.60
    nor
    0.59
     anymore
    0.55
     ataupun
    0.55
    任何人
    0.55
    Act Density 0.167%

    No Known Activations