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

    Neuronpedia

    INDEX
    Explanations

    disappear, slip, falls

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     realize
    0.40
    ลา
    0.39
     distributing
    0.39
     trying
    0.38
     realizing
    0.38
     Dispon
    0.38
     extrapolate
    0.37
     having
    0.37
     extracting
    0.37
     recognizing
    0.37
    POSITIVE LOGITS
     disappears
    0.64
     kerül
    0.63
     becomes
    0.61
     disappear
    0.59
     vengono
    0.57
     diventa
    0.55
     становятся
    0.55
    成为
    0.54
    成为了
    0.54
     gets
    0.54
    Act Density 0.009%

    No Known Activations