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

    Neuronpedia

    INDEX
    Explanations

    cscds

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    inar
    0.43
     alph
    0.43
     अल्फा
    0.41
    ンプー
    0.41
    ুলি
    0.40
    ukkh
    0.40
    ेंग
    0.39
    갤럭
    0.39
    ಬ್ಬಳ್ಳಿ
    0.39
     عض
    0.39
    POSITIVE LOGITS
    Cant
    0.43
     cant
    0.42
    z
    0.41
    d
    0.41
    ##
    0.40
    UTF
    0.40
    CTL
    0.40
    Crazy
    0.39
    Conversation
    0.39
    码
    0.39
    Act Density 0.000%

    No Known Activations