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

    Neuronpedia

    INDEX
    Explanations

    un- prefix followed by nouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ویت
    1.82
     Suy
    1.77
     Sarı
    1.75
    osit
    1.74
    bbe
    1.72
    ไต
    1.72
     attano
    1.72
    omponent
    1.71
     sams
    1.68
    ری
    1.67
    POSITIVE LOGITS
    ंचल
    1.77
    ITIES
    1.61
    悱
    1.52
    ဘူး
    1.47
    काशी
    1.46
     Realms
    1.46
     dares
    1.44
    circum
    1.42
    पणे
    1.41
    ski
    1.41
    Act Density 0.518%

    No Known Activations