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

    Neuronpedia

    INDEX
    Explanations

    code punctuation and comments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    男
    0.68
    감
    0.67
    ,#
    0.66
    ##
    0.65
    エレ
    0.64
     느끼
    0.63
    山
    0.63
    남
    0.63
    定制
    0.63
    -#
    0.63
    POSITIVE LOGITS
    oka
    0.78
     morte
    0.69
     ventre
    0.67
     perspiration
    0.65
    ocks
    0.65
     //
    0.65
     শিষ
    0.65
    cout
    0.63
    oko
    0.62
    Mj
    0.62
    Act Density 0.135%

    No Known Activations