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

    Neuronpedia

    INDEX
    Explanations

    finding working

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     основа
    0.46
    ambers
    0.42
     தலைவர்
    0.41
     ديسمبر
    0.41
    ༧
    0.41
    benchmark
    0.40
    桅
    0.40
     беско
    0.40
    ].”
    0.40
    ‐
    0.39
    POSITIVE LOGITS
     clots
    0.40
     Havre
    0.40
     tắm
    0.40
     venu
    0.40
     উঠ
    0.39
    শন
    0.39
     Sulfate
    0.39
    كلة
    0.39
    川
    0.39
     Dostupné
    0.38
    Act Density 0.002%

    No Known Activations