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

    Neuronpedia

    INDEX
    Explanations

    explaining why

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ，
    0.26
    、
    0.22
    erialize
    0.22
     -
    0.21
     and
    0.20
     cours
    0.20
    нім
    0.20
    0.20
    ।
    0.20
     ।
    0.20
    POSITIVE LOGITS
     Почему
    0.36
     đừng
    0.35
    Почему
    0.33
     почему
    0.32
    इसलिए
    0.30
     why
    0.29
     bukan
    0.29
     neden
    0.29
     tärke
    0.29
     नहीं
    0.29
    Act Density 0.212%

    No Known Activations