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

    Neuronpedia

    INDEX
    Explanations

    phrases describing methods or approaches

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

    way of doing things

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    cookieParser
    -0.47
    roli
    -0.44
     Normdatei
    -0.41
    BibitemShut
    -0.40
    crapers
    -0.39
    ograp
    -0.39
    igenous
    -0.38
    akers
    -0.38
     gynhyrchwyd
    -0.38
    ridescent
    -0.37
    POSITIVE LOGITS
     way
    0.69
     WAY
    0.61
     Way
    0.57
    GenerationType
    0.56
    Way
    0.53
     صفحۀ
    0.52
     assures
    0.52
     linkovi
    0.52
     wikipagina
    0.51
    WriteTagHelper
    0.51
    Act Density 0.005%

    No Known Activations