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

    Neuronpedia

    INDEX
    Explanations

    references to avoiding spoilers in narratives

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

    spoiler warnings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    enumii
    -0.61
    MessageTagHelper
    -0.56
    WithIOException
    -0.54
    BuildContext
    -0.49
     مشين
    -0.47
    iastes
    -0.47
    rungsseite
    -0.47
     estekak
    -0.47
    Lähteet
    -0.46
     NSCoder
    -0.46
    POSITIVE LOGITS
    Spoilers
    0.58
    Spoiler
    0.56
     spoiler
    0.56
     spoilers
    0.54
    spoiler
    0.52
     Spoiler
    0.50
    SPOILER
    0.47
     secret
    0.44
     SPOILERS
    0.43
     Spoilers
    0.43
    Act Density 0.207%

    No Known Activations