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

    Neuronpedia

    INDEX
    Explanations

    sequences of underscores which likely indicate formatting or separation in a document

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

    Code snippets and XML-like structures

    np_acts-logits-general · gemini-2.0-flash

    code symbols and keywords

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    gatsby
    -0.81
     StatelessWidget
    -0.73
    ResumeLayout
    -0.68
    synthesize
    -0.68
    bufio
    -0.67
     AttributeSet
    -0.67
    webElement
    -0.65
    pyplot
    -0.65
    bukkit
    -0.64
     EconPapers
    -0.63
    POSITIVE LOGITS
     becauſe
    0.82
     alſo
    0.73
     whoſe
    0.69
     neceſſ
    0.69
     myſelf
    0.68
     leaſt
    0.68
     pleaſure
    0.67
     Houſe
    0.67
     Jefus
    0.66
     ſmall
    0.64
    Act Density 0.378%

    No Known Activations