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

    Neuronpedia

    INDEX
    Explanations

    code imports and packages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     lewat
    0.32
    на
    0.31
     where
    0.31
     soooo
    0.31
     within
    0.30
     dari
    0.30
     making
    0.29
     rebut
    0.29
    zhu
    0.29
     whatever
    0.29
    POSITIVE LOGITS
    ILabel
    0.41
    EventType
    0.39
    Abstract
    0.39
    *;
    0.39
    HttpMethod
    0.38
    Inet
    0.38
    NameValuePair
    0.38
     ہوگا
    0.37
    enums
    0.35
     Amendment
    0.35
    Act Density 0.003%

    No Known Activations