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

    Neuronpedia

    INDEX
    Explanations

    numerical values, especially related to statistics or measurements

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

    Citations/references with bracketed years

    np_acts-logits-general · gemini-2.0-flash

    names and citations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    StoryboardSegue
    -0.83
     NSCoder
    -0.79
    GraphicsUnit
    -0.79
     auffi
    -0.74
     thiệu
    -0.72
     AssemblyVersion
    -0.71
     getItemCount
    -0.68
    fromCharCode
    -0.67
    tamol
    -0.67
    InSection
    -0.67
    POSITIVE LOGITS
    <bos>
    0.61
     Dar
    0.51
     res
    0.50
    zia
    0.49
    wil
    0.47
    ran
    0.46
    <eos>
    0.46
    fisk
    0.46
    zusch
    0.45
    Dar
    0.45
    Act Density 0.232%

    No Known Activations