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

    Neuronpedia

    INDEX
    Explanations

    references to system output and console logging functions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Code snippets or programming-related text

    np_acts-logits-general · gemini-2.0-flash

    plt.plot() and console.log() statements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Paglinawan
    -0.82
    AndroidJUnit
    -0.75
     mergeFrom
    -0.71
    utilisons
    -0.69
    windowFixed
    -0.68
     ©️
    -0.65
    AsUp
    -0.64
     ragaz
    -0.62
     @"/
    -0.62
    Демографія
    -0.60
    POSITIVE LOGITS
    .
    0.80
    .,
    0.57
    .~\
    0.57
    .,"
    0.56
    .);
    0.56
    มาะ
    0.55
    awtextra
    0.55
     .;
    0.53
    .),
    0.52
    yarnpkg
    0.51
    Act Density 0.056%

    No Known Activations