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

    Neuronpedia

    INDEX
    Explanations

    Option

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     requires
    0.98
    /
    0.97
     species
    0.91
     require
    0.87
     frequently
    0.87
     enjoys
    0.87
     are
    0.87
     or
    0.83
     undesirable
    0.82
    :
    0.82
    POSITIVE LOGITS
     ήταν
    1.61
     havde
    1.55
     είχε
    1.53
     miała
    1.45
     había
    1.40
     كانت
    1.40
     وكانت
    1.38
     aveva
    1.38
     étaient
    1.33
     있었다
    1.30
    Act Density 0.000%

    No Known Activations