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

    Neuronpedia

    INDEX
    Explanations

    assertive and definitive language related to conclusions and evaluations

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

    states and outcomes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    NewLabel
    -0.42
     Descubre
    -0.39
     hendes
    -0.38
     kvinder
    -0.38
     myſelf
    -0.37
     orquesta
    -0.37
     himſelf
    -0.36
     évêque
    -0.36
     prefeito
    -0.36
     chrétien
    -0.36
    POSITIVE LOGITS
     disambiguazione
    0.68
    LookAnd
    0.60
     CURIAM
    0.60
     propOrder
    0.59
    BufferException
    0.58
     виправивши
    0.58
    хьтан
    0.57
    onViewCreated
    0.56
    rrggbb
    0.56
    存于互联网档案馆
    0.55
    Act Density 0.200%

    No Known Activations