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

    Neuronpedia

    INDEX
    Explanations

    words related to people, especially names of people along with their profession or nationality.

    oai_token-act-pair · gemini-2.0-flash

    occupations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    viewDidLoad
    -0.72
    enschappelijke
    -0.66
    
    -0.59
    ￡
    -0.59
     DEPART
    -0.59
    JvmStatic
    -0.58
    ChromeDriver
    -0.57
     sanitaires
    -0.57
     défendre
    -0.56
     AttributeSet
    -0.55
    POSITIVE LOGITS
     poet
    0.57
     writer
    0.56
     author
    0.54
    rungsseite
    0.54
     self
    0.53
     noted
    0.51
     award
    0.51
    นัก
    0.49
     painter
    0.48
     historian
    0.48
    Act Density 1.766%

    No Known Activations