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

    Neuronpedia

    INDEX
    Explanations

    but

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     but
    0.72
     adalah
    0.72
    Start
    0.71
    But
    0.68
     אבל
    0.68
     pero
    0.66
     rifi
    0.66
    Are
    0.65
     Start
    0.65
     แต่
    0.64
    POSITIVE LOGITS
    etrot
    0.61
     reutil
    0.61
     بالإضافة
    0.61
    بية
    0.58
     EtOAc
    0.57
    convolve
    0.56
    することにより
    0.56
     ′
    0.55
     valorem
    0.55
    oforte
    0.55
    Act Density 0.003%

    No Known Activations