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

    Neuronpedia

    INDEX
    Explanations

    programming TypeError

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     aperto
    -1.45
    之后
    -1.44
     leyendo
    -1.41
    躂
    -1.35
    的
    -1.33
    ⿻
    -1.33
    providedIn
    -1.32
    }
    -1.29
    蕯
    -1.29
     prezenta
    -1.27
    POSITIVE LOGITS
    .
    1.54
    きましたが
    1.44
    嵜
    1.40
     remplacé
    1.38
    気で
    1.38
     dégust
    1.30
    そこで
    1.30
    かっ
    1.23
    ↵
    1.23
     plateado
    1.22
    Act Density 0.003%

    No Known Activations