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

    Neuronpedia

    INDEX
    Explanations

    also known as

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    FTA
    -0.07
     Changed
    -0.06
     forfeiture
    -0.06
    KeyPress
    -0.06
     місце
    -0.06
     mux
    -0.06
     Aviation
    -0.06
     renewal
    -0.06
    意识
    -0.06
    ko
    -0.06
    POSITIVE LOGITS
     название
    0.07
     mask
    0.06
    (cam
    0.06
     '",
    0.06
    asc
    0.06
     reports
    0.06
    QRSTUV
    0.06
    (dispatch
    0.06
    [contains
    0.06
    "});↵
    0.06
    Act Density 0.042%

    No Known Activations