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

    Neuronpedia

    INDEX
    Explanations

    statements of personal perspective or expression of individual thoughts

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

    i think

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     AssemblyCompany
    -0.79
     enfans
    -0.57
    adaptiveStyles
    -0.54
     HasFactory
    -0.52
    AddTagHelper
    -0.50
    localVar
    -0.47
    İstin
    -0.46
     liderança
    -0.46
     arşivlendi
    -0.46
     compartilhar
    -0.45
    POSITIVE LOGITS
    Indented
    0.43
    Identyfik
    0.42
     poisoned
    0.41
    BarItem
    0.41
     Seidel
    0.40
     ap
    0.40
    ABEL
    0.39
     Mackey
    0.39
     Ok
    0.38
     poisoning
    0.38
    Act Density 0.009%

    No Known Activations