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

    Neuronpedia

    INDEX
    Explanations

    and or

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     L
    0.61
     (
    0.59
     is
    0.55
     Has
    0.51
     V
    0.50
     has
    0.49
    impinan
    0.48
    iles
    0.47
     K
    0.47
     D
    0.47
    POSITIVE LOGITS
    !),
    0.79
    !).
    0.78
    !!)
    0.71
    !)
    0.71
     admittedly
    0.66
    oretically
    0.64
    ！)
    0.63
     кстати
    0.63
     übrigens
    0.62
     oczywiście
    0.61
    Act Density 0.234%

    No Known Activations