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

    Neuronpedia

    INDEX
    Explanations

    defining variables like n and x

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <b>
    0.96
    <strong>
    0.92
    Continue
    0.91
    การ
    0.89
    <start_of_image>
    0.88
     đám
    0.84
    <i>
    0.84
    <h2>
    0.83
    續
    0.82
    สร
    0.81
    POSITIVE LOGITS
    <unused1178>
    1.77
    <unused1177>
    1.75
    <unused1174>
    1.74
    <unused1624>
    1.73
    <unused938>
    1.72
    <unused149>
    1.71
    <unused1226>
    1.70
     بی
    1.69
    <unused1217>
    1.68
    <unused1208>
    1.67
    Act Density 0.003%

    No Known Activations