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

    Neuronpedia

    INDEX
    Explanations

    making mistakes or accidents

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ку
    0.47
    কে
    0.45
     Landscapes
    0.45
    硋
    0.43
     ملا
    0.42
    Seeing
    0.42
    Recommended
    0.42
    蒖
    0.41
    atura
    0.41
    椋
    0.41
    POSITIVE LOGITS
     convert
    0.50
     discount
    0.49
     wyjątk
    0.46
    。
    0.43
     critic
    0.43
     clavier
    0.42
     renouvel
    0.41
     núi
    0.41
    noi
    0.41
    ্যাল
    0.41
    Act Density 0.008%

    No Known Activations