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

    Neuronpedia

    INDEX
    Explanations

    FROM :

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    otene
    0.38
     開始
    0.37
    ่าย
    0.32
     covariates
    0.32
     tảo
    0.31
     किनार
    0.31
     των
    0.31
    স্য
    0.31
     основных
    0.31
     両
    0.30
    POSITIVE LOGITS
     the
    0.36
     een
    0.35
    خي
    0.34
    िश्व
    0.34
     he
    0.34
     an
    0.33
     evidently
    0.33
     said
    0.32
     यूनाइटेड
    0.32
     itib
    0.32
    Act Density 0.023%

    No Known Activations