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

    Neuronpedia

    INDEX
    Explanations

    specific names and titles related to individuals and roles in various contexts

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

    names and roles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     autorytatywna
    -0.60
    rubin
    -0.47
    MergeFrom
    -0.42
    ANTLR
    -0.40
    一股
    -0.39
    srcs
    -0.38
     архивлан
    -0.38
    embeds
    -0.37
     crap
    -0.36
    rul
    -0.36
    POSITIVE LOGITS
     suaminya
    0.54
     acompañada
    0.53
    RenderAtEndOf
    0.51
    Personendaten
    0.48
     novio
    0.48
     asamblea
    0.47
    SequentialGroup
    0.47
     ejecutivo
    0.46
     navideños
    0.45
    ConstraintMaker
    0.45
    Act Density 0.037%

    No Known Activations