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

    Neuronpedia

    INDEX
    Explanations

    punctuation and code snippets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    לק
    0.46
     camino
    0.41
     hopp
    0.38
     acetaldehyde
    0.38
     tempor
    0.38
    خن
    0.38
     asseg
    0.38
    unica
    0.37
    更为
    0.37
     aniline
    0.37
    POSITIVE LOGITS
    (//
    0.47
     下载
    0.42
     Publisher
    0.41
    ប្រទេស
    0.40
     downloads
    0.40
    er
    0.39
     প্রকাশক
    0.39
    ;
    0.39
     यू
    0.38
    {
    0.38
    Act Density 0.013%

    No Known Activations