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

    Neuronpedia

    INDEX
    Explanations

    file extensions and domains

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    (
    0.72
    .
    0.65
    $$
    0.64
    ​​
    0.62
    ي
    0.58
    \\
    0.57
    i
    0.56
     lateral
    0.56
    েরও
    0.56
     =====
    0.55
    POSITIVE LOGITS
    ᐟ
    0.95
    png
    0.85
    jpg
    0.82
     godine
    0.76
    exe
    0.73
     године
    0.72
    JPG
    0.71
    elni
    0.69
    astico
    0.68
     október
    0.68
    Act Density 0.457%

    No Known Activations