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

    Neuronpedia

    INDEX
    Explanations

    code imports and file paths

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    முகச்
    0.30
    मलव
    0.28
    र्सन
    0.28
     सीजीएल
    0.27
     carboxylic
    0.27
    ාල
    0.26
    ार्मिक
    0.26
    鳇
    0.26
    醪
    0.26
     Absolutely
    0.26
    POSITIVE LOGITS
    /
    0.54
    _
    0.52
    utils
    0.45
    /[
    0.39
    /_
    0.39
    /__
    0.38
    _/
    0.38
    __
    0.37
    \
    0.37
    Utils
    0.36
    Act Density 0.024%

    No Known Activations