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

    Neuronpedia

    INDEX
    Explanations

    references to figures, tables, and visual representations in documents

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

    Referring to figures, diagrams, or screenshots

    np_acts-logits-general · gemini-2.0-flash

    visual references or depictions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    contentLoaded
    -0.79
     AssemblyTitle
    -0.69
    writeFieldEnd
    -0.67
    enderror
    -0.67
    omiast
    -0.66
    Viitteet
    -0.65
    الإنجليزية
    -0.65
    phosa
    -0.63
    ftagPool
    -0.63
    出版年
    -0.63
    POSITIVE LOGITS
     pictured
    1.40
    如下图
    1.25
    如图
    1.21
     shown
    1.19
     screenshot
    1.17
     Figure
    1.16
    Figure
    1.12
     diagram
    1.09
     illustrated
    1.06
    pictured
    1.05
    Act Density 1.184%

    No Known Activations