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

    Neuronpedia

    INDEX
    Explanations

    silver ring, hours, addEvent

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    cares
    0.42
     najleps
    0.41
     Plague
    0.41
     quizá
    0.40
    គ្មាន
    0.40
    ads
    0.40
    тали
    0.39
    rystals
    0.38
    لاك
    0.38
     sali
    0.38
    POSITIVE LOGITS
     researched
    0.44
    研究所
    0.43
    instance
    0.39
     برش
    0.37
     pt
    0.35
    就已经
    0.35
     instance
    0.35
    ப்படும்
    0.35
    实例
    0.35
    ी
    0.34
    Act Density 0.000%

    No Known Activations