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

    Neuronpedia

    INDEX
    Explanations

    references to appendices in a document

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

    appendix sections

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    KommentareTeilen
    -0.75
    ագրություններ
    -0.53
    "]="
    -0.51
    riwal
    -0.50
    🏾
    -0.48
    makeConstraints
    -0.48
     FontWeight
    -0.47
    Stal
    -0.46
    tagHelperRunner
    -0.46
    ‍♀️
    -0.45
    POSITIVE LOGITS
     Appendix
    1.20
    Appendix
    1.16
     appendix
    1.14
    APPENDIX
    0.95
     APPENDIX
    0.93
     appendices
    0.92
     Appendices
    0.86
    appendix
    0.82
    Appendices
    0.75
     Anhang
    0.74
    Act Density 0.015%

    No Known Activations