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

    Neuronpedia

    INDEX
    Explanations

    code and file paths

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    670
    -0.08
    sport
    -0.07
    哭
    -0.07
    691
    -0.06
    ỗi
    -0.06
     STREAM
    -0.06
    nex
    -0.06
     dummy
    -0.06
    วไป
    -0.06
     GPI
    -0.06
    POSITIVE LOGITS
    ازي
    0.07
    Sil
    0.06
    _Ch
    0.06
     reservation
    0.06
     свобод
    0.06
     outstanding
    0.06
     الجز
    0.06
     средства
    0.06
     ability
    0.06
     Reservation
    0.06
    Act Density 0.476%

    No Known Activations