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

    Neuronpedia

    INDEX
    Explanations

    looking at, in everything

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     {
    0.73
     {(
    0.69
    (['
    0.67
    Tis
    0.67
    ("
    0.66
     !(
    0.65
    (["
    0.63
     &
    0.63
    ροι
    0.63
     カジュアル
    0.62
    POSITIVE LOGITS
    …
    0.94
    ...
    0.94
    －－
    0.94
     väldigt
    0.91
    ...).
    0.90
    ……
    0.89
     veryvery
    0.88
    ,...
    0.88
    ...”
    0.87
    …</
    0.87
    Act Density 0.286%

    No Known Activations