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

    Neuronpedia

    INDEX
    Explanations

    references to academic work and research output in textual form

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

    photographs and recent publications

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     anſ
    -0.43
    ilanth
    -0.40
     <>",
    -0.39
     müßte
    -0.39
     müsse
    -0.39
     Cecil
    -0.39
     touch
    -0.37
     Taz
    -0.36
    DotNetBar
    -0.36
     tuong
    -0.36
    POSITIVE LOGITS
    AndEndTag
    0.61
    Aholisi
    0.49
    IndentedString
    0.49
    ViewImports
    0.47
    ClientSize
    0.47
    AISSEE
    0.46
    findpost
    0.46
     bénéficiaire
    0.45
     endblock
    0.44
    StoreMessageInfo
    0.44
    Act Density 0.002%

    No Known Activations