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

    Neuronpedia

    INDEX
    Explanations

    Process Discovery

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    y
    0.50
                
    0.50
    यों
    0.47
    ut
    0.43
    kepsilon
    0.43
    疚
    0.43
     качества
    0.42
     இரண்ட
    0.42
     Ирина
    0.42
     ១
    0.42
    POSITIVE LOGITS
    ة
    0.43
    विध
    0.42
    倶
    0.42
    first
    0.42
     sobri
    0.42
    േഖ
    0.41
    isPlaying
    0.40
    Ouest
    0.39
    Frequent
    0.39
    ඓ
    0.39
    Act Density 0.000%

    No Known Activations