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

    Neuronpedia

    INDEX
    Explanations

    Code symbols

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     music
    -0.06
     massac
    -0.06
    이어
    -0.06
     Catholic
    -0.06
    (bt
    -0.06
    thew
    -0.06
    theses
    -0.06
     poetry
    -0.06
    舌
    -0.06
     criticisms
    -0.06
    POSITIVE LOGITS
    ?>">
↵
    0.07
    DOMAIN
    0.06
    _img
    0.06
     التاريخ
    0.06
     mannen
    0.06
    OfYear
    0.06
    δε
    0.06
     disproportion
    0.06
     относится
    0.06
    ↑
    0.06
    Act Density 0.139%

    No Known Activations