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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Caribbean
    -0.06
    modelo
    -0.06
    ans
    -0.06
     Hudson
    -0.06
     convincing
    -0.06
    .minimum
    -0.06
    мещ
    -0.06
    ardown
    -0.06
    reads
    -0.06
    ANS
    -0.06
    POSITIVE LOGITS
     ration
    0.07
    $output
    0.06
     техні
    0.06
    iện
    0.06
     стала
    0.06
    (priv
    0.06
    ****************************************************************
    0.06
    .lat
    0.06
    ‌پدی
    0.06
    )*(
    0.06
    Act Density 0.063%

    No Known Activations