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

    Neuronpedia

    INDEX
    Explanations

    questions and answers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    上述
    0.42
     వీడియో
    0.41
    但在
    0.39
     উত্তেজ
    0.39
     但是
    0.39
     the
    0.38
     максима
    0.38
     لیکن
    0.38
    但是
    0.38
     hadronic
    0.38
    POSITIVE LOGITS
     যেকোন
    0.42
     smiley
    0.41
    क्राइब
    0.40
     povos
    0.40
     Bereichen
    0.39
     frowning
    0.39
    anyo
    0.38
     চাওয়া
    0.38
     Einrichtungen
    0.38
    SetFloat
    0.38
    Act Density 2.331%

    No Known Activations