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

    Neuronpedia

    INDEX
    Explanations

    programming language syntax elements, particularly identifiers and operators

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

    class name "

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ientras
    -0.68
     EconPapers
    -0.68
     OnInit
    -0.67
     indígen
    -0.66
    ſcher
    -0.64
    iſten
    -0.60
    unately
    -0.58
    PreExecute
    -0.57
    hematical
    -0.56
    retudo
    -0.56
    POSITIVE LOGITS
    Class
    0.89
     Class
    0.88
     CLASS
    0.80
    class
    0.74
    CLASS
    0.73
     class
    0.69
     Classes
    0.66
    Classes
    0.63
     clase
    0.60
     classe
    0.60
    Act Density 0.010%

    No Known Activations