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

    Neuronpedia

    INDEX
    Explanations

    separation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    被列入
    -0.07
    瓖
    -0.07
     Diễn
    -0.07
    就餐
    -0.07
    vable
    -0.07
    佛山市
    -0.07
    攻打
    -0.06
    Associated
    -0.06
    bp
    -0.06
     Night
    -0.06
    POSITIVE LOGITS
     thumbnails
    0.07
    𣗋
    0.07
    ᆺ
    0.07
    _CAL
    0.07
    Leg
    0.07
    _track
    0.07
    拒绝
    0.07
    command
    0.07
    уд
    0.07
     defender
    0.06
    Act Density 0.007%

    No Known Activations