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

    Neuronpedia

    INDEX
    Explanations

    Alternative splicing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    蝤
    -0.07
    ㏓
    -0.07
    كت
    -0.07
    десь
    -0.07
    称之
    -0.07
    包袱
    -0.07
    込め
    -0.07
    use
    -0.06
    窸
    -0.06
    鼩
    -0.06
    POSITIVE LOGITS
     journalists
    0.09
    أنواع
    0.08
     Partition
    0.08
     المواد
    0.08
     foam
    0.07
     filmmakers
    0.07
    	labels
    0.07
     activated
    0.07
    _skills
    0.07
    paths
    0.07
    Act Density 0.008%

    No Known Activations