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

    Neuronpedia

    INDEX
    Explanations

    relationships and lineage

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     grueso
    0.39
    ্লাই
    0.37
    C
    0.35
    UIT
    0.33
    Z
    0.33
    X
    0.32
    <0xB2>
    0.32
    ጫ
    0.32
    Command
    0.31
     compi
    0.30
    POSITIVE LOGITS
     of
    0.57
     ofthe
    0.56
    ของการ
    0.54
     geworden
    0.54
     của
    0.52
     घोषित
    0.50
    នៃ
    0.50
    ของ
    0.49
     của
    0.49
     contender
    0.49
    Act Density 0.028%

    No Known Activations