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

    Neuronpedia

    INDEX
    Explanations

    numerical patterns or sequences

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

    Hexadecimal byte representations

    np_acts-logits-general · gemini-2.0-flash

    hexadecimal numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     resourceCulture
    -0.82
    WEBPACK
    -0.68
    oredCriteria
    -0.67
    CppMethod
    -0.61
    /**
    -0.61
     AssemblyTitle
    -0.60
    contentLoaded
    -0.59
    basicConfig
    -0.59
    invokeLater
    -0.58
    Personensuche
    -0.57
    POSITIVE LOGITS
    B
    0.58
     Manner
    0.58
     Ways
    0.57
    a
    0.56
    ProductService
    0.55
     Rollo
    0.54
    туаль
    0.53
    C
    0.53
     Mercu
    0.53
    
    0.53
    Act Density 0.741%

    No Known Activations