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

    Neuronpedia

    INDEX
    Explanations

    lists and specific advice

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ہے۔
    0.31
     takže
    0.31
     wobei
    0.30
     gdyż
    0.30
     ہوں۔
    0.28
     ذریع
    0.27
     ponieważ
    0.27
    }.
    0.27
     sehingga
    0.27
     ہیں۔
    0.27
    POSITIVE LOGITS
    ،
    0.46
    ，
    0.46
    ၊
    0.42
    ,
    0.42
    ፣
    0.39
    、
    0.36
     ,
    0.34
     there
    0.34
     thì
    0.33
     ،
    0.31
    Act Density 0.666%

    No Known Activations