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

    Neuronpedia

    INDEX
    Explanations

    Grafana

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     KI
    0.39
    adilla
    0.38
    rein
    0.38
    insol
    0.36
    ēng
    0.36
    OrderID
    0.36
    Kiss
    0.36
     ফাঁ
    0.35
     Ki
    0.34
     Kis
    0.34
    POSITIVE LOGITS
    屯
    0.42
     Truman
    0.41
     Architect
    0.40
     tung
    0.39
     thrills
    0.39
     Jewels
    0.39
     Москва
    0.38
     Acad
    0.38
     jew
    0.38
     glam
    0.38
    Act Density 0.007%

    No Known Activations