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

    Neuronpedia

    INDEX
    Explanations

    complex data structures or formats, particularly in programming or data representation contexts

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

    Numbers inside curly brackets

    np_acts-logits-general · gemini-2.0-flash

    mathematical expressions and code snippets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    GraphicsUnit
    -0.70
    ftagPool
    -0.68
    UnusedPrivate
    -0.56
    AddHtmlAttribute
    -0.55
    Jeografia
    -0.55
    matchCondition
    -0.53
    oa̍t
    -0.52
    fillType
    -0.52
    transQ
    -0.51
    itinéraire
    -0.51
    POSITIVE LOGITS
     valable
    0.38
     дописавши
    0.35
     compé
    0.34
     taza
    0.33
    wsdl
    0.32
     évaluation
    0.32
     FileSystem
    0.31
     competição
    0.31
     compétition
    0.30
     fédéral
    0.30
    Act Density 0.617%

    No Known Activations