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

    Neuronpedia

    INDEX
    Explanations

    key

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    チャ
    -0.07
    .health
    -0.07
    电
    -0.07
     ROOM
    -0.06
     onlara
    -0.06
    ذیر
    -0.06
    арі
    -0.06
    OURS
    -0.06
    ุตบอล
    -0.06
    INATION
    -0.06
    POSITIVE LOGITS
     глаз
    0.08
    ApiKey
    0.08
     Wh
    0.07
    apiKey
    0.07
    (cid
    0.07
    _KEY
    0.07
     Deutsche
    0.07
     Shack
    0.06
    +[
    0.06
     
    0.06
    Act Density 0.006%

    No Known Activations