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

    Neuronpedia

    INDEX
    Explanations

    printing values in code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     том
    0.37
     apiece
    0.37
     transcribed
    0.37
     tom
    0.36
    が表示
    0.36
    通知
    0.36
    appendTo
    0.36
    lify
    0.35
     نمایش
    0.35
    दयाल
    0.35
    POSITIVE LOGITS
    putchar
    0.65
     putchar
    0.62
     exista
    0.45
     put
    0.41
    рга
    0.41
     '.')
    0.39
     puts
    0.39
    Mn
    0.39
     undergoes
    0.39
    క్
    0.38
    Act Density 0.018%

    No Known Activations