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

    Neuronpedia

    INDEX
    Explanations

    spatial coordinates

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ق
    1.43
    ك
    1.28
     in
    0.96
    ра
    0.94
    است
    0.93
    お
    0.93
    అ
    0.93
    від
    0.91
    ס
    0.91
    অ
    0.90
    POSITIVE LOGITS
    and
    1.20
     coordinates
    1.07
    ną
    1.00
    ে
    0.97
    larından
    0.95
     fica
    0.94
     좌표
    0.94
    '
    0.91
    of
    0.90
    ib
    0.87
    Act Density 0.006%

    No Known Activations