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

    Neuronpedia

    INDEX
    Explanations

    isn't it? confirmation questions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    -$
    0.36
    चन
    0.36
    ครื่อง
    0.36
    জিন
    0.35
    ಿಯನ್ನು
    0.35
     interl
    0.35
    であることが
    0.35
    ⑨
    0.35
    均匀
    0.35
     CharPtr
    0.35
    POSITIVE LOGITS
    ?
    0.84
    ؟
    0.84
    ？
    0.79
    ?!
    0.72
    ?(
    0.70
    ?\
    0.64
    ؟.
    0.64
     그죠
    0.61
    ?.
    0.61
    ?[
    0.59
    Act Density 0.009%

    No Known Activations