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

    Neuronpedia

    INDEX
    Explanations

    about

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    芝
    -0.08
     CGFloat
    -0.08
    izer
    -0.07
     derby
    -0.07
    ifiées
    -0.07
     Derby
    -0.07
    ahlt
    -0.07
     Codable
    -0.07
    metro
    -0.07
     Witt
    -0.07
    POSITIVE LOGITS
     DISCLAIM
    0.09
     nemen
    0.08
     vlast
    0.08
     புக
    0.08
     начинают
    0.08
    0.08
     ગુજરાતી
    0.08
     красиво
    0.08
     будут
    0.07
    Emotion
    0.07
    Act Density 0.009%
    No Known Activations