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

    Neuronpedia

    INDEX
    Explanations

    special formatting and specific notation in mathematical or formal texts

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

    diagram, theorem, list items

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    TagMode
    -0.88
    AddTagHelper
    -0.65
     للمعارف
    -0.57
     насељу
    -0.55
     extranjero
    -0.54
     ejecutivo
    -0.54
     desmotivaciones
    -0.54
     NSCoder
    -0.53
    setVerticalGroup
    -0.51
    حياته
    -0.50
    POSITIVE LOGITS
    "]();
    0.41
    >')
    0.40
    ()])
    0.37
    >`;
    0.37
    resave
    0.36
     perist
    0.35
    ()%
    0.34
    Namaste
    0.33
    :@
    0.33
    ()['
    0.33
    Act Density 0.104%

    No Known Activations