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

    Neuronpedia

    INDEX
    Explanations

    syntax structures and specific formatting elements in code or data interfaces

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

    numerical analysis tests

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    DockStyle
    -0.41
     cancelación
    -0.39
    XmlRootElement
    -0.38
     cláus
    -0.37
    niosek
    -0.37
     catalán
    -0.34
     sanitarios
    -0.33
     violación
    -0.32
     denuncia
    -0.31
     detención
    -0.31
    POSITIVE LOGITS
    0.71
     EconPapers
    0.56
    interopRequire
    0.56
    writeFieldEnd
    0.55
    ConstraintMaker
    0.54
    әрмәләр
    0.53
     مرئيه
    0.52
    цездатний
    0.52
     pinulongan
    0.52
     Photocase
    0.52
    Act Density 0.015%

    No Known Activations