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

    Neuronpedia

    INDEX
    Explanations

    self. and function calls

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     सबसे
    0.46
    use
    0.44
     Best
    0.44
     सर्वोत्तम
    0.44
    Best
    0.44
    /
    0.44
    的最佳
    0.43
    ➥
    0.42
    e
    0.41
    Use
    0.41
    POSITIVE LOGITS
     medulla
    0.49
     gonorrhea
    0.46
    蔘
    0.45
     այդ
    0.45
     clump
    0.44
     infest
    0.44
     triglycer
    0.43
    COTT
    0.43
     neurologic
    0.43
     gazed
    0.43
    Act Density 0.006%

    No Known Activations