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

    Neuronpedia

    INDEX
    Explanations

    punctuations and their associated frequencies

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

    names and citations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     nonUne
    -0.66
     ویکی‌پدی
    -0.63
    点此举报
    -0.60
    цездатний
    -0.59
    expandindo
    -0.59
    Tembelea
    -0.59
    хьтан
    -0.59
     CreateTagHelper
    -0.57
    Спасылкі
    -0.55
     pinulongan
    -0.54
    POSITIVE LOGITS
     ๆ
    0.47
    }{*}{
    0.40
    |()
    0.40
     ().
    0.38
     .=
    0.38
    [toxicity=0]
    0.38
     *);
    0.37
     (),
    0.36
    gman
    0.36
    orteur
    0.35
    Act Density 0.072%

    No Known Activations