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

    Neuronpedia

    INDEX
    Explanations

    study and learning

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Cosm
    0.58
     Directorate
    0.57
    欺
    0.55
    ქმ
    0.55
     Assay
    0.55
     विचारों
    0.54
    鍱
    0.53
    Calibration
    0.52
     listopada
    0.52
     নৃত্য
    0.52
    POSITIVE LOGITS
     buddy
    1.33
    buddy
    1.08
     buddies
    1.06
     Buddy
    1.03
    Buddy
    0.94
     coach
    0.89
     partner
    0.88
     bud
    0.85
     Budd
    0.79
    伙伴
    0.78
    Act Density 0.041%

    No Known Activations