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

    Neuronpedia

    INDEX
    Explanations

    but, though, contrast

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     tutor
    0.44
     woodworking
    0.42
     déliv
    0.41
     tutoring
    0.40
     FFA
    0.40
     fft
    0.40
    aghe
    0.40
    লীগ
    0.39
     ffm
    0.39
     বিজ্ঞ
    0.38
    POSITIVE LOGITS
     идея
    0.46
    钀
    0.44
    ственными
    0.43
     ಮನೆಯ
    0.42
    spiritual
    0.42
     ወይም
    0.42
     философии
    0.42
    著
    0.42
     عندنا
    0.42
    ても
    0.42
    Act Density 0.005%

    No Known Activations