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

    Neuronpedia

    INDEX
    Explanations

    representations of intent or user directives

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

    version critiques or notes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    aarrggbb
    -0.78
    ########.
    -0.64
    OGND
    -0.61
    HandlerContext
    -0.58
     Administrativna
    -0.58
     useAppContext
    -0.55
     Photocase
    -0.55
    fillType
    -0.54
     незавершена
    -0.53
     '\\;'
    -0.53
    POSITIVE LOGITS
    enterOuterAlt
    0.34
    ground
    0.34
    ève
    0.34
    DIF
    0.33
    m
    0.33
     preview
    0.32
     предо
    0.32
    werker
    0.32
    ViewImports
    0.31
    uolo
    0.31
    Act Density 0.001%

    No Known Activations