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

    Neuronpedia

    INDEX
    Explanations

    words related to size, text manipulation and GUI objects

    oai_token-act-pair · gemini-2.0-flash

    Code related to properties

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ++;
    -0.68
    [$
    -0.68
    [
    -0.66
     ;
    -0.64
    (
    -0.62
    OGND
    -0.62
    fromCharCode
    -0.60
    ;
    -0.60
    CloseOperation
    -0.59
    {};
    -0.59
    POSITIVE LOGITS
     tayo
    0.62
     itſelf
    0.56
    Rhestr
    0.54
     uſed
    0.54
     EconPapers
    0.53
    elon
    0.52
     Majefty
    0.51
     MÁ
    0.51
     Basta
    0.49
    χρι
    0.49
    Act Density 0.241%

    No Known Activations