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

    Neuronpedia

    INDEX
    Explanations

    strings of digits or dollar signs followed by digits

    oai_token-act-pair · gemini-2.0-flash

    Numerical values

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     thousands
    -1.65
     thousand
    -1.55
    thousands
    -1.44
     Thousands
    -1.42
     hundreds
    -1.34
    Thousands
    -1.31
     THOUS
    -1.30
    thousand
    -1.14
    hundreds
    -1.13
     Hundreds
    -1.10
    POSITIVE LOGITS
     NSCoder
    0.69
    DoubleQuotes
    0.66
    chitz
    0.63
    IntoConstraints
    0.62
     Normdatei
    0.62
     lenker
    0.60
    contentLoaded
    0.59
    protoimpl
    0.58
    URLException
    0.56
     تضيفلها
    0.56
    Act Density 1.256%

    No Known Activations