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

    Neuronpedia

    INDEX
    Explanations

    concerns and motivations related to reputation and its pursuit

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

    follow fake flight updating

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    NewReader
    -0.44
     Aguilar
    -0.36
     Burke
    -0.35
     nochmals
    -0.34
    -0.34
    eros
    -0.33
    ={[
    -0.33
     Murillo
    -0.32
    slidesToShow
    -0.32
    Navigate
    -0.32
    POSITIVE LOGITS
    AndEndTag
    0.67
    rrggbb
    0.57
    цездатний
    0.49
     gynhyrchwyd
    0.47
    httphttps
    0.46
    ImageContext
    0.45
    webElementGuid
    0.45
     unknownFields
    0.45
    tagHelperRunner
    0.44
    Tikang
    0.43
    Act Density 0.109%

    No Known Activations