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

    Neuronpedia

    INDEX
    Explanations

    code structure and definitions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     außergewöhn
    0.39
    Mientras
    0.39
    История
    0.38
     deiner
    0.38
    Еще
    0.38
     teplot
    0.38
    بی
    0.38
    FilesIn
    0.38
    uldade
    0.37
    性和
    0.37
    POSITIVE LOGITS
     (
    0.73
    。(
    0.70
    。（
    0.66
     including
    0.64
    （
    0.64
     (#
    0.64
     wobei
    0.64
     (\
    0.63
    。
    0.63
     (“
    0.61
    Act Density 0.194%

    No Known Activations