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

    Neuronpedia

    INDEX
    Explanations

    0

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     hồ
    -0.08
     AlertDialog
    -0.08
     instinct
    -0.07
     bed
    -0.07
     tụ
    -0.07
    火锅
    -0.07
    .Thread
    -0.07
    _that
    -0.07
     psychiatrist
    -0.07
    (feed
    -0.07
    POSITIVE LOGITS
    IG
    0.08
    enzie
    0.07
    _NONE
    0.07
     choose
    0.07
    줴
    0.07
    казывает
    0.06
    (tok
    0.06
    0.06
     WR
    0.06
     OVERRIDE
    0.06
    Act Density 0.047%

    No Known Activations