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

    Neuronpedia

    INDEX
    Explanations

    left right

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    声响
    -0.08
    inis
    -0.07
    纵横
    -0.07
    /network
    -0.07
     schn
    -0.07
    不仅可以
    -0.07
    กอง
    -0.07
    ⴼ
    -0.07
    isObject
    -0.07
    nga
    -0.07
    POSITIVE LOGITS
    Sentence
    0.08
     Shopping
    0.07
     facade
    0.07
     .....
    0.07
     Meta
    0.07
     ',↵
    0.07
    CREATE
    0.07
    Patient
    0.06
    0.06
    Server
    0.06
    Act Density 0.005%

    No Known Activations