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

    Neuronpedia

    INDEX
    Explanations

    contrast and differences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    вера
    0.41
    燊
    0.41
     Bühne
    0.39
     Bä
    0.37
    nå
    0.37
     Jako
    0.36
    Far
    0.36
    Beijing
    0.36
    準
    0.36
     Kathmandu
    0.35
    POSITIVE LOGITS
     setMessage
    0.43
     एसएमएस
    0.43
     tit
    0.40
     deacetyl
    0.40
     people
    0.40
     contrast
    0.39
     looking
    0.38
     शौ
    0.38
     वाय
    0.38
     Contrast
    0.38
    Act Density 0.000%

    No Known Activations