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

    Neuronpedia

    INDEX
    Explanations

    #

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     وحت
    -0.07
    突然
    -0.07
    为契机
    -0.06
     HDMI
    -0.06
     Paths
    -0.06
     GRE
    -0.06
    揭牌
    -0.06
    .Network
    -0.06
    突如其
    -0.06
     הק
    -0.06
    POSITIVE LOGITS
    uchos
    0.09
    olina
    0.07
    صر
    0.07
    ,,,,
    0.07
    违反
    0.07
    /detail
    0.07
    coll
    0.07
    廷
    0.07
    namespace
    0.06
    ificio
    0.06
    Act Density 0.000%

    No Known Activations