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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    AttributedString
    -0.08
     society
    -0.06
    andExpect
    -0.06
     hl
    -0.06
     Kaz
    -0.06
    ούς
    -0.06
    estival
    -0.06
    ustral
    -0.06
    quotelev
    -0.06
     societal
    -0.06
    POSITIVE LOGITS
     Differences
    0.06
    kı
    0.06
     Slave
    0.06
     JOHN
    0.06
     Savannah
    0.06
     UserController
    0.06
    /.↵↵
    0.06
     EVERY
    0.06
     ه
    0.06
     Events
    0.06
    Act Density 0.065%

    No Known Activations