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

    Neuronpedia

    INDEX
    Explanations

    code inspection and javascript

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    البه
    0.42
     LEAR
    0.41
     लर्निंग
    0.41
     diathermy
    0.40
    वाह
    0.39
    ጬ
    0.38
    โยชน์
    0.38
     proclaim
    0.38
    一覧
    0.37
     स्ट्रेट
    0.37
    POSITIVE LOGITS
     Inspe
    0.53
     Inspection
    0.52
     inspection
    0.49
    JavaScript
    0.48
    Inspection
    0.48
     JavaScript
    0.47
     javafx
    0.46
    inspection
    0.45
     inspections
    0.45
    Javascript
    0.45
    Act Density 0.003%

    No Known Activations