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

    Neuronpedia

    INDEX
    Explanations

    numerical values and their contextual placements within text

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

    width and height properties

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    +#+#
    -0.49
    人
    -0.35
    +#+
    -0.34
    脚注の使い方
    -0.33
    UserScript
    -0.32
    :][
    -0.30
    FBI
    -0.29
     FBI
    -0.27
    flink
    -0.27
    \[
    -0.27
    POSITIVE LOGITS
    innerWidth
    0.77
    sidemargin
    0.72
     width
    0.72
    ſchen
    0.66
     Paglinawan
    0.64
     vertical
    0.64
     horizontal
    0.63
     rectangular
    0.63
     الحره
    0.63
     flexible
    0.61
    Act Density 0.083%

    No Known Activations