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

    Neuronpedia

    INDEX
    Explanations

    the/this

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .reward
    -0.07
    ](
    -0.07
     dancing
    -0.07
    (map
    -0.07
     waitFor
    -0.07
     Tow
    -0.07
     ensures
    -0.06
    Warehouse
    -0.06
     Mechanical
    -0.06
    -ball
    -0.06
    POSITIVE LOGITS
    INLINE
    0.06
     incompet
    0.06
     userType
    0.06
     звіль
    0.06
     Cec
    0.06
    AMIL
    0.06
    кій
    0.06
     UserDefaults
    0.06
     �
    0.06
     pošk
    0.06
    Act Density 0.186%

    No Known Activations