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

    Neuronpedia

    INDEX
    Explanations

    arguments and reasoning related to logic and analytical thinking

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

    logic and reasoning

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    nodoc
    -0.54
    MessageOf
    -0.50
     fotográfico
    -0.50
     Lokales
    -0.50
    middels
    -0.50
    Décès
    -0.47
    DataAnnotations
    -0.46
    Tembelea
    -0.46
    SharedCtor
    -0.45
     Sünde
    -0.43
    POSITIVE LOGITS
    ScopeManager
    0.46
     كومونز
    0.39
    tagHelperRunner
    0.38
    なら
    0.37
    ingale
    0.36
    исленность
    0.36
     OMITBAD
    0.36
    Dann
    0.35
     Luck
    0.35
     Jungfrau
    0.35
    Act Density 0.253%

    No Known Activations