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

    Neuronpedia

    INDEX
    Explanations

    task, annotate

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    লা
    0.44
    უნ
    0.44
     Ranges
    0.43
    ep
    0.42
    ेला
    0.42
    λαν
    0.40
     توز
    0.39
    াম
    0.39
    გომ
    0.39
    ുകള്‍
    0.39
    POSITIVE LOGITS
     Cahill
    0.52
     комментария
    0.49
     riman
    0.48
     torrential
    0.48
     hydroelectric
    0.47
     lige
    0.47
     leng
    0.45
     ré
    0.45
     জাহাঙ্গীর
    0.44
     ምግብ
    0.44
    Act Density 0.000%

    No Known Activations