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

    Neuronpedia

    INDEX
    Explanations

    comparing limitations vs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    2
    0.61
    5
    0.59
    8
    0.54
    9
    0.52
    Char
    0.52
    3
    0.52
    في
    0.49
    4
    0.49
    7
    0.48
    Just
    0.48
    POSITIVE LOGITS
     применение
    0.50
     solicita
    0.48
     distinguer
    0.48
     semelhantes
    0.46
     commemorating
    0.45
     применять
    0.45
     PGR
    0.45
     비슷한
    0.45
     Ramadan
    0.44
     tinkering
    0.44
    Act Density 0.002%

    No Known Activations