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

    Neuronpedia

    INDEX
    Explanations

    note followed by colon

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    你就
    0.47
     ચૂક
    0.44
    utérus
    0.43
    graphHead
    0.43
     فکر
    0.43
    你了
    0.43
     왜
    0.43
     спасибо
    0.43
    impanan
    0.43
     рынке
    0.42
    POSITIVE LOGITS
     that
    0.50
    ม
    0.48
    This
    0.48
    م
    0.48
     bahwa
    0.47
    ता
    0.46
    ł
    0.46
    The
    0.46
    з
    0.45
     This
    0.45
    Act Density 0.062%

    No Known Activations