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

    Neuronpedia

    INDEX
    Explanations

    Location and data points

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <unused1095>
    0.47
    ᥣ
    0.46
    <unused436>
    0.46
    ্ে
    0.45
    <unused146>
    0.45
    <unused242>
    0.45
    <unused1081>
    0.44
    <unused213>
    0.44
    <unused589>
    0.44
    <unused592>
    0.44
    POSITIVE LOGITS
    Location
    0.44
    ICO
    0.41
    UN
    0.40
     Location
    0.39
    位置
    0.38
     location
    0.37
    Satellite
    0.35
    >
    0.35
    Long
    0.35
    5
    0.35
    Act Density 0.001%

    No Known Activations