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

    Neuronpedia

    INDEX
    Explanations

    references to code imports or dependencies in programming context

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

    from outside

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    참고
    -0.46
    ORE
    -0.38
    密钥
    -0.38
    appcompat
    -0.36
    mentación
    -0.35
    perate
    -0.35
    цен
    -0.35
     Gardener
    -0.33
     theoretically
    -0.33
    casting
    -0.32
    POSITIVE LOGITS
     <>",
    0.64
    URLException
    0.58
    ThroughAttribute
    0.57
    RectangleBorder
    0.56
     otomatig
    0.54
    AndEndTag
    0.53
    UrlResolution
    0.50
    numerusform
    0.49
    iſen
    0.48
    richTextPanel
    0.48
    Act Density 0.001%

    No Known Activations