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

    Neuronpedia

    INDEX
    Explanations

    structured data or programming-related keywords indicative of function calls and arguments in code

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

    Code, numbers, and symbols

    np_acts-logits-general · gemini-2.0-flash

    English review prompt

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    '}';
    -0.59
    QtCore
    -0.54
    ช
    -0.54
     High
    -0.50
     prospects
    -0.50
     train
    -0.49
    LookAnd
    -0.49
     Pan
    -0.49
    remera
    -0.49
     high
    -0.49
    POSITIVE LOGITS
     Chicano
    0.74
     argint
    0.73
    AxisAlignment
    0.71
     bénévoles
    0.70
    évaluateur
    0.70
     AssemblyProduct
    0.70
     Lordships
    0.67
     Eurosport
    0.66
     theologians
    0.66
    persky
    0.65
    Act Density 2.702%

    No Known Activations