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

    Neuronpedia

    INDEX
    Explanations

    mentions of numbers and quantities, often introducing lists or quantifiable problems and solutions

    oai_token-act-pair · gemini-2.0-flash

    key concepts in research

    np_token-act-pair-logits · gpt-4o-mini

    One/Another

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    AccessorTable
    -0.59
    ValueStyle
    -0.57
     defaultstate
    -0.55
     ModelExpression
    -0.54
    BeginContext
    -0.49
    पया
    -0.47
    PerformLayout
    -0.46
     intptr
    -0.45
     AssemblyCompany
    -0.45
    Хьажоргаш
    -0.43
    POSITIVE LOGITS
     area
    0.70
     possible
    0.68
     key
    0.63
     elements
    0.63
    addContainerGap
    0.62
     potential
    0.60
     strategy
    0.60
     aspect
    0.60
     overriding
    0.59
     aspects
    0.57
    Act Density 3.314%

    No Known Activations