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

    Neuronpedia

    INDEX
    Explanations

    suffering and reduction

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    self
    0.52
     self
    0.50
    u
    0.42
    your
    0.42
    http
    0.40
     announced
    0.40
    ŭ
    0.40
    x
    0.40
    startswith
    0.40
    announced
    0.39
    POSITIVE LOGITS
     thừa
    0.48
     इत्यादी
    0.46
     RCLCPP
    0.46
     পার্থক্য
    0.42
    壹百
    0.42
     συνα
    0.42
     सर्
    0.42
     ณ
    0.42
     ओर
    0.41
     Số
    0.41
    Act Density 0.002%

    No Known Activations