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

    Neuronpedia

    INDEX
    Explanations

    questions and punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     पद्धतीने
    0.28
     أ
    0.25
     emphas
    0.25
     Aad
    0.25
     a
    0.24
    ಲಿನ
    0.24
    𝗧
    0.24
    *",
    0.24
    াড়ার
    0.24
    έ
    0.24
    POSITIVE LOGITS
    ?
    0.40
    ？
    0.39
    ។
    0.39
    ؟
    0.38
    。
    0.36
    !
    0.35
    ?!
    0.34
     ؟
    0.34
    ؟.
    0.33
    !?
    0.33
    Act Density 0.986%

    No Known Activations