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

    Neuronpedia

    INDEX
    Explanations

    terms indicating usefulness or importance

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

    importance and benefit

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    IsMutable
    -0.51
    AndEndTag
    -0.50
    AppMethodBeat
    -0.46
    itability
    -0.44
    Vorlage
    -0.43
    Ҭ
    -0.43
    IFO
    -0.42
    SaveVideo
    -0.41
    lioz
    -0.41
    plex
    -0.40
    POSITIVE LOGITS
     importante
    0.44
     importants
    0.44
    IndentedString
    0.42
     important
    0.42
     importantes
    0.41
    tagHelperRunner
    0.40
     중요
    0.39
     OMITBAD
    0.39
     económico
    0.39
     productivo
    0.38
    Act Density 0.130%

    No Known Activations