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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate negative or critical attitudes

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

    parts, suffixes, or bases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    SuspendLayout
    -0.43
     oídos
    -0.41
     Wohnen
    -0.40
     comunicarse
    -0.40
     sentirse
    -0.40
     sentarse
    -0.37
     שוליים
    -0.37
     istrinya
    -0.35
     správ
    -0.35
     propOrder
    -0.35
    POSITIVE LOGITS
    expandindo
    0.72
     Enigma
    0.63
     monop
    0.60
     Vim
    0.59
     convention
    0.57
     Midas
    0.57
    PAIGN
    0.57
    -<
    0.57
    -}
    0.56
    indler
    0.56
    Act Density 0.166%

    No Known Activations