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

    Neuronpedia

    INDEX
    Explanations

    names of people involved in communication or transactions

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

    names and titles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     celebs
    -0.52
    Hentet
    -0.50
     footballer
    -0.47
     celebrities
    -0.47
     pintados
    -0.46
    Erreferentziak
    -0.45
     ünl
    -0.45
    GEBURTSDATUM
    -0.45
     crimen
    -0.45
     millionaires
    -0.44
    POSITIVE LOGITS
     staff
    0.97
     Staff
    0.79
     Assistant
    0.78
    staff
    0.77
     personnel
    0.74
    Staff
    0.71
     assistant
    0.70
     담
    0.69
    Assistant
    0.69
     Manager
    0.67
    Act Density 0.037%

    No Known Activations