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

    Neuronpedia

    INDEX
    Explanations

    spacing characters or whitespace in a text

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

    with unusual capitalization or characters

    np_acts-logits-general · gemini-2.0-flash

    Communicated about

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    期刊论文
    -0.48
    <eos>
    -0.46
     فريبيس
    -0.45
    containsKey
    -0.45
    RectangleBorder
    -0.44
     ceded
    -0.42
     
    -0.42
     apud
    -0.41
     antiga
    -0.41
    twimg
    -0.41
    POSITIVE LOGITS
     препратки
    0.92
     ProtoMessage
    0.84
     TextAppearance
    0.76
     purpoſe
    0.69
    tagHelperRunner
    0.67
     mergeFrom
    0.66
    eseorang
    0.64
     itſelf
    0.63
     raiſ
    0.63
    djangoproject
    0.62
    Act Density 0.049%

    No Known Activations