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

    Neuronpedia

    INDEX
    Explanations

    references to names and collaborations in academic or formal contexts

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

    Follows the letters X, Y, or J

    np_acts-logits-general · gemini-2.0-flash

    YijiActor

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    enumi
    -0.51
     mantequilla
    -0.49
     الاطلاع
    -0.46
    monial
    -0.45
    ISupport
    -0.44
    ycznie
    -0.43
     Hospice
    -0.43
    orElseThrow
    -0.42
    IONAL
    -0.42
    otrop
    -0.42
    POSITIVE LOGITS
    OGND
    0.66
    ########.
    0.65
    uming
    0.60
    ings
    0.59
    ancang
    0.58
    ushan
    0.57
    ItemBackground
    0.56
    ujian
    0.55
    __":
    0.55
    ouwen
    0.55
    Act Density 0.154%

    No Known Activations