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

    Neuronpedia

    INDEX
    Explanations

    quoted speech and citations within the text

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

    Text within brackets

    np_acts-logits-general · gemini-2.0-flash

    bracketed text

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     CreateTagHelper
    -1.12
    AnchorStyles
    -0.89
    SharedDtor
    -0.88
     '\\;'
    -0.85
    setVerticalGroup
    -0.84
    ViewFeatures
    -0.84
    :✨
    -0.84
     Roskov
    -0.83
     pinulongan
    -0.81
    styleType
    -0.81
    POSITIVE LOGITS
    中略
    1.04
    sic
    1.02
    ..]
    0.69
    ,]
    0.67
    ]
    0.65
    ...]
    0.64
    inaudible
    0.63
    ..)
    0.59
    redacted
    0.59
    .]
    0.59
    Act Density 0.129%

    No Known Activations