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

    Neuronpedia

    INDEX
    Explanations

    res.method calls

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     JavaScript
    0.43
    (`${
    0.40
     ajouter
    0.39
     parallax
    0.39
     Reli
    0.38
    MakeRect
    0.38
     Javascript
    0.38
     Ô
    0.38
     হচ্ছেন
    0.37
    徹底
    0.37
    POSITIVE LOGITS
    res
    0.86
     res
    0.86
    next
    0.68
     next
    0.62
    Next
    0.53
     Res
    0.51
    kn
    0.49
    reply
    0.49
    callback
    0.48
     resampling
    0.47
    Act Density 0.005%

    No Known Activations