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

    Neuronpedia

    INDEX
    Explanations

    cleaning, feeding, or disposing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ki
    0.43
     runde
    0.42
     anderem
    0.42
     verdens
    0.41
    "){
    0.40
     zehn
    0.39
     kontinu
    0.39
     manuf
    0.39
     whatnot
    0.39
     jaune
    0.38
    POSITIVE LOGITS
    بود
    0.42
     Mood
    0.40
    })$
    0.39
     ঘা
    0.38
    보
    0.38
    ాలు
    0.37
    તી
    0.36
     Forbes
    0.36
    })\
    0.36
    의
    0.36
    Act Density 0.065%

    No Known Activations