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

    Neuronpedia

    INDEX
    Explanations

    organizations and appreciation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Sleeping
    0.45
    䔀
    0.45
    Healthcare
    0.44
    ská
    0.44
    ћа
    0.44
    Andrea
    0.43
    ِّف
    0.43
    West
    0.43
    skou
    0.43
    си
    0.42
    POSITIVE LOGITS
     three
    0.59
     indices
    0.53
     directories
    0.53
     populaires
    0.52
     datar
    0.51
     activist
    0.50
     six
    0.48
     four
    0.48
     blocks
    0.48
    3
    0.48
    Act Density 0.001%

    No Known Activations