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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "new"

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

    new object creation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     resourceCulture
    -0.74
     <<<<<<<<<<<<<<
    -0.72
    richTextPanel
    -0.70
     betweenstory
    -0.69
    exitRule
    -0.65
    GraphicsUnit
    -0.65
    ftagPool
    -0.60
    +#+#
    -0.58
    CppMethod
    -0.56
    tagHelperRunner
    -0.55
    POSITIVE LOGITS
     poly
    0.45
    new
    0.45
     new
    0.44
    std
    0.40
     proto
    0.40
    NEAR
    0.40
     pou
    0.40
     mixed
    0.39
     sap
    0.38
    OneToOne
    0.38
    Act Density 0.007%

    No Known Activations