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

    Neuronpedia

    INDEX
    Explanations

    describing excellence and beauty

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     idk
    0.66
     fucking
    0.65
     fake
    0.62
     específico
    0.62
     shitty
    0.62
     nějak
    0.61
     merda
    0.60
    そもそも
    0.57
     uptick
    0.57
     봤
    0.56
    POSITIVE LOGITS
     exhilarating
    0.85
     prachtige
    0.80
     unsurpassed
    0.79
     exquisitely
    0.76
     unrivalled
    0.74
     beautifully
    0.72
     breathtaking
    0.71
     richly
    0.71
     unforgettable
    0.70
     unparalleled
    0.70
    Act Density 0.024%

    No Known Activations