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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    =f
    -0.07
    Translate
    -0.07
    /users
    -0.07
    gain
    -0.07
     ά
    -0.06
    updates
    -0.06
     drugs
    -0.06
     ylim
    -0.06
     tong
    -0.06
    kj
    -0.06
    POSITIVE LOGITS
    $arr
    0.07
     ngờ
    0.06
     특
    0.06
    .While
    0.06
    Portfolio
    0.06
    >@
    0.06
    淡
    0.06
     hailed
    0.06
     medida
    0.06
    .IsEmpty
    0.06
    Act Density 0.009%

    No Known Activations