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

    Neuronpedia

    INDEX
    Explanations

    numbers in option tags

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Lösung
    0.46
     INDIA
    0.44
    ологі
    0.44
     DELHI
    0.43
     Dharmendra
    0.43
     Anleitung
    0.43
    DataXYZ
    0.42
    腕時計
    0.42
    UTONIUM
    0.42
    嬅
    0.42
    POSITIVE LOGITS
    it
    0.68
    on
    0.63
    pe
    0.60
     it
    0.59
    n
    0.59
    N
    0.54
    по
    0.52
     n
    0.52
    pl
    0.51
    be
    0.50
    Act Density 0.000%

    No Known Activations