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

    Neuronpedia

    INDEX
    Explanations

    ce

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     municipality
    -0.07
     landscape
    -0.07
     caregiver
    -0.07
    地理
    -0.07
     Drink
    -0.07
    EncodingException
    -0.07
    tour
    -0.06
    ounter
    -0.06
    具有良好
    -0.06
    เม
    -0.06
    POSITIVE LOGITS
    ﻔ
    0.07
    ﻈ
    0.07
    	Size
    0.07
     реш
    0.07
    �
    0.07
    𝜋
    0.07
    Anywhere
    0.07
     dated
    0.06
    ocal
    0.06
    𝇚
    0.06
    Act Density 0.002%

    No Known Activations