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

    Neuronpedia

    INDEX
    Explanations

    latex caption format options

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    వే
    0.40
    ะนั้น
    0.37
     শোনা
    0.37
    IDA
    0.37
    FULLY
    0.37
    AAF
    0.36
    ﻯ
    0.36
    مي
    0.36
    ILIA
    0.35
    EDA
    0.35
    POSITIVE LOGITS
    ]{
    0.54
    =
    0.51
    !}{
    0.43
    ={
    0.43
    #,
    0.41
    ={(
    0.41
     pdf
    0.40
    ,...,
    0.40
    [],
    0.40
    }{
    0.39
    Act Density 0.001%

    No Known Activations