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

    Neuronpedia

    INDEX
    Explanations

    references to figures and tables in the text

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

    figure references

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     للمعارف
    -0.66
     ModelExpression
    -0.61
     estekak
    -0.54
     populate
    -0.52
     arXiv
    -0.48
     $_(
    -0.48
     ARXIV
    -0.48
     Populate
    -0.47
     reorder
    -0.47
     consultato
    -0.46
    POSITIVE LOGITS
    Fig
    0.55
     Fig
    0.52
    fig
    0.50
    FIG
    0.47
     FIGURE
    0.46
     FIG
    0.45
    Figs
    0.44
    FIGURE
    0.43
    figure
    0.42
    diagram
    0.41
    Act Density 0.058%

    No Known Activations