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

    Neuronpedia

    INDEX
    Explanations

    references to fictional characters and names

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

    Text found within code or data structures

    np_acts-logits-general · gemini-2.0-flash

    Harry Potter, Hello World

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ivelany
    -0.66
    adaptiveStyles
    -0.59
     ostavi
    -0.59
     fotográfico
    -0.58
    webElementGuid
    -0.56
     financeira
    -0.55
     فريبيس
    -0.55
     videa
    -0.55
     zoude
    -0.55
     cír
    -0.54
    POSITIVE LOGITS
    les
    0.35
     Favourite
    0.35
     favourite
    0.32
     editor
    0.32
     البر
    0.30
    addHeader
    0.30
    Favourite
    0.30
    waz
    0.30
     brom
    0.29
     boys
    0.29
    Act Density 0.270%

    No Known Activations