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

    Neuronpedia

    INDEX
    Explanations

    multilingual text snippets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     содержа
    0.27
     Elektrokhimiya
    0.25
     없
    0.25
     ";
    0.24
    ek
    0.23
     memory
    0.23
    守护
    0.23
    ee
    0.23
    gn
    0.23
    货
    0.23
    POSITIVE LOGITS
     شركة
    0.32
    pciones
    0.29
     comparability
    0.29
     言っ
    0.29
     einigen
    0.28
     somew
    0.28
     იყოს
    0.28
     einige
    0.28
    ⅼ
    0.27
     ب
    0.27
    Act Density 0.002%

    No Known Activations