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

    Neuronpedia

    INDEX
    Explanations

    academic writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    냥
    -0.07
    guard
    -0.06
    eydi
    -0.06
     усі
    -0.06
     LIN
    -0.06
    шел
    -0.06
     seed
    -0.06
    ์ก
    -0.06
     nghị
    -0.06
    ρούν
    -0.06
    POSITIVE LOGITS
    .swt
    0.06
     Fellow
    0.06
     innov
    0.06
    (Some
    0.06
     "$(
    0.06
     chiar
    0.06
    .LogInformation
    0.06
     utilized
    0.06
     lessen
    0.06
    (pipe
    0.06
    Act Density 0.094%

    No Known Activations