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

    Neuronpedia

    INDEX
    Explanations

    historical terms followed by noun classifiers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     کوئی
    1.00
     없
    0.94
     ennen
    0.92
    저
    0.92
     कोई
    0.91
     জানা
    0.90
    많은
    0.90
     확인할
    0.90
    Cannot
    0.89
     저
    0.89
    POSITIVE LOGITS
    化的
    1.13
    ization
    0.96
    isierung
    0.94
    isation
    0.93
    isiert
    0.90
    ización
    0.88
    化
    0.87
     ingenuity
    0.87
    ised
    0.84
    ুয়ার
    0.83
    Act Density 0.297%

    No Known Activations