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

    Neuronpedia

    INDEX
    Explanations

    operating systems

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    }
    0.44
    ské
    0.44
     sondern
    0.43
    these
    0.43
    יא
    0.42
    skim
    0.41
     дополнительные
    0.41
    ִי
    0.41
    ួន
    0.41
    Les
    0.40
    POSITIVE LOGITS
     정확
    0.52
     Irrigation
    0.50
     geçen
    0.48
     negociación
    0.48
     syrup
    0.47
     April
    0.46
     wavy
    0.46
     celery
    0.46
     qualitative
    0.45
     pasada
    0.45
    Act Density 0.003%

    No Known Activations