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

    Neuronpedia

    INDEX
    Explanations

    use of the word "that"

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     snippetHide
    -1.13
     صوتيه
    -1.00
     EconPapers
    -1.00
     defaultstate
    -0.94
     Мексичка
    -0.88
    abestanden
    -0.87
    verwijspagina
    -0.87
    UserScript
    -0.85
    InputBorder
    -0.85
     NSCoder
    -0.84
    POSITIVE LOGITS
     the
    0.84
     you
    0.77
     some
    0.76
     when
    0.73
     after
    0.72
     during
    0.71
     if
    0.70
     by
    0.69
     since
    0.69
    <bos>
    0.68
    Act Density 0.234%

    No Known Activations