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

    Neuronpedia

    INDEX
    Explanations

    references to personal professions and roles in society

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

    accountant, banker

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     scaling
    -0.40
    交渉
    -0.39
    ICIAS
    -0.37
     Wachs
    -0.36
     Streifen
    -0.36
     Horowitz
    -0.35
     nhờ
    -0.35
     Spitze
    -0.35
     Tasche
    -0.35
    ichern
    -0.34
    POSITIVE LOGITS
     '\\;'
    0.66
     ſta
    0.65
     ſch
    0.61
    цездатний
    0.59
     ſte
    0.58
    новништво
    0.55
    ſelves
    0.55
     ThemeData
    0.54
     Monfieur
    0.53
    bitField
    0.52
    Act Density 0.110%

    No Known Activations