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

    Neuronpedia

    INDEX
    Explanations

    feature comparison and distinction

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    藿
    0.37
    borist
    0.34
    шов
    0.34
     taker
    0.33
     Nor
    0.33
     saison
    0.33
     Bhagavato
    0.32
    ையோ
    0.32
     psychologist
    0.32
     coroner
    0.31
    POSITIVE LOGITS
    }%
    0.31
    jsx
    0.30
    cores
    0.29
    {}
    0.29
    ({})
    0.29
    ناك
    0.28
     [])
    0.28
    )</
    0.28
    mf
    0.28
    illac
    0.27
    Act Density 0.006%

    No Known Activations