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

    Neuronpedia

    INDEX
    Explanations

    the word "all."

    oai_token-act-pair · gemini-2.0-flash

    all

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     role
    -0.52
     تضيفلها
    -0.48
     steg
    -0.46
    sivity
    -0.46
    UserRole
    -0.43
    ือง
    -0.43
    ↵↵
    -0.43
     
    -0.43
    ändig
    -0.43
     step
    -0.42
    POSITIVE LOGITS
    reactstrap
    0.76
     للمعارف
    0.70
    StoreMessageInfo
    0.69
     enfans
    0.68
    andaag
    0.65
     שוליים
    0.65
     مرئيه
    0.64
     faſt
    0.62
    Espèce
    0.62
     avoit
    0.62
    Act Density 0.863%

    No Known Activations