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

    Neuronpedia

    INDEX
    Explanations

    quantitative data and statistical analysis

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

    Numbers between delimiters

    np_acts-logits-general · gemini-2.0-flash

    numbers 16 through 19

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ⓧ
    -0.78
    setupUi
    -0.64
     Kyiv
    -0.59
    olulu
    -0.58
    Билгалдахарш
    -0.56
     Kiev
    -0.54
     Torrey
    -0.54
     Erişim
    -0.54
    AndEndTag
    -0.52
    InjectAttribute
    -0.52
    POSITIVE LOGITS
    十八
    0.72
     XVIII
    0.67
     seventeen
    0.65
     eighteen
    0.65
    eigh
    0.61
     Seventeen
    0.61
     Eighteenth
    0.61
     sixteen
    0.60
     nineteen
    0.60
     eighteenth
    0.59
    Act Density 0.628%

    No Known Activations