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
    ]}
    -0.09
    日正式
    -0.07
    培养学生
    -0.07
    '];?>
    -0.07
    第三届
    -0.07
     görüyor
    -0.07
    提出
    -0.06
    舍
    -0.06
    )}↵↵
    -0.06
    .onSubmit
    -0.06
    POSITIVE LOGITS
     Fib
    0.08
    zł
    0.07
    rance
    0.07
    ulk
    0.07
    (ht
    0.07
     리
    0.07
    alu
    0.07
     Fits
    0.07
     Packing
    0.07
     Merlin
    0.07
    Act Density 0.015%

    No Known Activations