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

    Neuronpedia

    INDEX
    Explanations

    stages and seasons

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    𝘰
    0.47
    Simulator
    0.47
    Watercolor
    0.45
    యా
    0.45
    Assert
    0.44
    А
    0.44
    우리
    0.43
    मु
    0.43
    Certified
    0.42
    Viewport
    0.42
    POSITIVE LOGITS
     gives
    0.43
     schme
    0.43
     injections
    0.42
     geven
    0.41
     atak
    0.41
     inf
    0.41
     ll
    0.41
     give
    0.40
     donnent
    0.40
     gibt
    0.39
    Act Density 0.002%

    No Known Activations