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

    Neuronpedia

    INDEX
    Explanations

    into

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     instead
    0.48
     poiché
    0.44
     iako
    0.42
     または
    0.39
     lacked
    0.39
     is
    0.39
     ("
    0.38
     has
    0.38
     &
    0.38
     or
    0.38
    POSITIVE LOGITS
    a
    0.70
     overdrive
    0.55
     uncharted
    0.54
     adulthood
    0.52
     realms
    0.48
    ه
    0.46
     oblivion
    0.43
     खासा
    0.43
    Discussion
    0.43
    短短
    0.43
    Act Density 0.023%

    No Known Activations