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

    Neuronpedia

    INDEX
    Explanations

    HTML tags and elements in markup language

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

    HTML image tags

    np_acts-logits-general · gemini-2.0-flash

    HTML tags like `<img>`, `<input>`

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     of
    -0.61
     and
    -0.55
     ogen
    -0.54
    menuStrip
    -0.53
    nicas
    -0.52
    rohr
    -0.52
     ins
    -0.50
    úly
    -0.50
    穫
    -0.50
     Mehl
    -0.49
    POSITIVE LOGITS
    ="#"><
    1.14
     myſelf
    0.90
    ագրություններ
    0.84
    verwijspagina
    0.81
     poffible
    0.80
     ويكيميديا
    0.78
     pleaſure
    0.78
     uſed
    0.77
     greateſt
    0.77
     ་་
    0.77
    Act Density 0.081%

    No Known Activations