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

    Neuronpedia

    INDEX
    Explanations

    uncertainty

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    needed
    -0.07
    若
    -0.07
    ccion
    -0.06
     начала
    -0.06
    NotEmpty
    -0.06
    车
    -0.06
     sonra
    -0.06
     Austrian
    -0.06
     hug
    -0.06
    yster
    -0.06
    POSITIVE LOGITS
    retim
    0.07
     objekt
    0.07
     Intelli
    0.07
     downside
    0.07
    Factory
    0.06
     marty
    0.06
    301
    0.06
     psik
    0.06
     salty
    0.06
    .Conn
    0.06
    Act Density 0.022%

    No Known Activations