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

    Neuronpedia

    INDEX
    Explanations

    Linear Algebra and Statistics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ഏറെ
    0.37
    انوں
    0.36
     inade
    0.36
     விழ
    0.36
    eine
    0.33
    खाव
    0.33
    бурга
    0.33
    这才
    0.33
     \%,
    0.33
    මින්
    0.32
    POSITIVE LOGITS
     kõik
    0.37
    More
    0.37
     More
    0.36
    Linear
    0.36
     všetky
    0.36
     Algebra
    0.35
     MORE
    0.35
     Linear
    0.35
     Alphabet
    0.34
    ాతీయ
    0.34
    Act Density 0.000%

    No Known Activations