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

    Neuronpedia

    INDEX
    Explanations

    references to individuals and their roles or accomplishments

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

    professional and personal life details

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     jobs
    -0.32
    MfG
    -0.28
     Jobs
    -0.28
     рабочих
    -0.28
     formerly
    -0.27
     gewerb
    -0.27
    Grüße
    -0.27
     Rechten
    -0.26
    Grüsse
    -0.26
     job
    -0.26
    POSITIVE LOGITS
     hobbies
    0.94
    volunteer
    0.86
    Volunteer
    0.85
     volunteer
    0.84
    Married
    0.81
     Hobbies
    0.81
     Volunteer
    0.79
     hobby
    0.78
     philanthrop
    0.78
    interests
    0.78
    Act Density 0.014%

    No Known Activations