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

    Neuronpedia

    INDEX
    Explanations

    occurrences of strong emphasis or significance markers, such as asterisks

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

    Downregulated, Exposure, Ag, P, Socio, U

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ThroughAttribute
    -0.73
     queſta
    -0.71
     dAtA
    -0.69
    makeConstraints
    -0.68
     BoxDecoration
    -0.66
    complexContent
    -0.65
    tagHelperRunner
    -0.64
    -0.64
     informée
    -0.63
    GraphicsUnit
    -0.63
    POSITIVE LOGITS
    ="@+
    0.29
    jublj
    0.27
     £
    0.27
    PathParam
    0.26
    ✭✭
    0.26
     (£
    0.25
    傾
    0.25
     "
    0.25
    േ
    0.25
     (!)
    0.24
    Act Density 0.038%

    No Known Activations