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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    常委会
    -0.07
     chain
    -0.06
    מסך
    -0.06
    ="",
    -0.06
     dissent
    -0.06
    mlink
    -0.06
     полу
    -0.06
    做大做强
    -0.06
    Runs
    -0.06
    双赢
    -0.06
    POSITIVE LOGITS
     Toll
    0.07
     Sp
    0.07
     Foot
    0.07
     glyc
    0.07
    ♢
    0.07
     Pic
    0.07
    덤
    0.07
     Patterson
    0.07
     Andrews
    0.07
    滟
    0.07
    Act Density 0.013%

    No Known Activations