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

    Neuronpedia

    INDEX
    Explanations

    words like "respected", "school", "evolution"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    nění
    0.32
    racción
    0.31
     البعض
    0.31
    ূল্যে
    0.30
     usamos
    0.30
     mendorong
    0.29
    acketing
    0.29
     设备
    0.29
    ścio
    0.29
    avasena
    0.29
    POSITIVE LOGITS
    の
    0.51
    ка
    0.43
    а
    0.42
    의
    0.39
    с
    0.39
    ದ
    0.38
    те
    0.38
    и
    0.37
    ი
    0.37
    у
    0.37
    Act Density 0.094%

    No Known Activations