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

    Neuronpedia

    INDEX
    Explanations

    mathematical calculations or conversions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ۱۵
    0.80
     ۲۰
    0.78
     ۸
    0.77
     nth
    0.76
     mundane
    0.75
     ۵
    0.73
     ۷
    0.72
     ouro
    0.71
     ۹
    0.70
     ۱۹
    0.70
    POSITIVE LOGITS
    3
    0.90
    4
    0.87
    5
    0.81
    9
    0.80
    7
    0.76
    6
    0.74
    8
    0.74
    0
    0.72
    <unused889>
    0.72
    ⃣
    0.72
    Act Density 0.850%

    No Known Activations