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

    Neuronpedia

    INDEX
    Explanations

    That

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .)}
    -0.63
    MessageTagHelper
    -0.60
    .',
    -0.58
     }=\
    -0.54
    .';
    -0.54
    ]`
    -0.53
    )​
    -0.52
     $]$
    -0.52
     $\}$
    -0.52
    )'
    -0.52
    POSITIVE LOGITS
     (
    0.81
     चीज़ों
    0.75
     disambiguazione
    0.65
    kháu
    0.65
    abestanden
    0.65
     ویکی‌پدی
    0.64
     définiti
    0.64
    <bos>
    0.62
    （
    0.61
     familières
    0.59
    Act Density 0.003%

    No Known Activations