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

    Neuronpedia

    INDEX
    Explanations

    adaptable extension

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     નવી
    0.41
    ველი
    0.39
     совет
    0.39
     refined
    0.39
     сім
    0.38
     совершен
    0.38
    πισ
    0.37
     семья
    0.37
     وصحبه
    0.37
     families
    0.36
    POSITIVE LOGITS
    রীণ
    0.42
    颌
    0.39
     projected
    0.38
     حسب
    0.38
    电气
    0.38
    帽
    0.38
     अंदा
    0.38
     ≥
    0.37
    Trail
    0.37
     hails
    0.37
    Act Density 0.002%

    No Known Activations