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

    Neuronpedia

    INDEX
    Explanations

    not

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    UTES
    -0.07
    数据
    -0.07
     gold
    -0.07
     onData
    -0.06
     ary
    -0.06
    �n
    -0.06
     sadd
    -0.06
    assertTrue
    -0.06
     cleaning
    -0.06
     Yıl
    -0.06
    POSITIVE LOGITS
     resulted
    0.06
    πά
    0.06
    -products
    0.06
     Goth
    0.06
     dönemde
    0.06
    (fn
    0.06
     Speakers
    0.06
     sàn
    0.06
    /ex
    0.06
    ──
    0.05
    Act Density 0.017%

    No Known Activations