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

    Neuronpedia

    INDEX
    Explanations

    references to specific national identities or governmental entities

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

    nationalities and roles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    BufferException
    -0.66
    featureID
    -0.58
     betweenstory
    -0.56
     للمعارف
    -0.54
    NameInMap
    -0.53
    TargetException
    -0.53
    awtextra
    -0.52
    URLException
    -0.51
    RTDA
    -0.50
    EndContext
    -0.49
    POSITIVE LOGITS
     managers
    0.45
     officials
    0.44
     analysts
    0.43
     staffers
    0.41
     experts
    0.39
     Svenska
    0.38
    ætter
    0.38
     employees
    0.38
     bosses
    0.38
     uppgifter
    0.38
    Act Density 0.047%

    No Known Activations