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

    Neuronpedia

    INDEX
    Explanations

    current dates

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    =
    0.52
    作物
    0.41
    =-\
    0.40
    Notebook
    0.38
    ht
    0.37
    رب
    0.37
     महोत्सव
    0.37
     insertions
    0.36
    OKA
    0.36
    rict
    0.35
    POSITIVE LOGITS
    ↵
    0.65
    an
    0.49
    на
    0.49
    л
    0.49
    ій
    0.48
    ли
    0.48
    ம்
    0.48
    е
    0.48
    І
    0.48
     doğal
    0.48
    Act Density 0.013%

    No Known Activations