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

    Neuronpedia

    INDEX
    Explanations

    package deals and timeframes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    _
    0.51
    ated
    0.47
    .
    0.45
    pati
    0.44
     marketable
    0.44
    =
    0.44
     taxes
    0.44
    :
    0.43
     money
    0.42
     sales
    0.41
    POSITIVE LOGITS
    骅
    0.52
     Ettha
    0.49
     thuring
    0.49
     Brasile
    0.48
     Bibliothek
    0.47
     Bibliothe
    0.46
     prophetic
    0.45
    pickMenu
    0.45
     தேர்த
    0.44
    の色
    0.43
    Act Density 0.002%

    No Known Activations