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

    Neuronpedia

    INDEX
    Explanations

    code identifiers and punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ergewöhn
    0.44
    Anything
    0.42
    歙
    0.41
     аспек
    0.40
    abilität
    0.40
    溶液
    0.39
    वेद
    0.39
    TAK
    0.39
     двох
    0.39
    矾
    0.38
    POSITIVE LOGITS
     ,
    0.50
    !,
    0.47
    =
    0.47
     tersebut
    0.46
     yours
    0.45
     =
    0.44
     it
    0.43
    ;,
    0.43
     aforementioned
    0.42
     parliament
    0.41
    Act Density 0.006%

    No Known Activations