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

    Neuronpedia

    INDEX
    Explanations

    were

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Alt
    -0.07
     Mexico
    -0.06
    (chart
    -0.06
    Mexico
    -0.06
    рат
    -0.06
     spells
    -0.06
     Discrim
    -0.06
     الأول
    -0.06
     lä
    -0.06
     governing
    -0.06
    POSITIVE LOGITS
     홈페이지
    0.06
     ire
    0.06
     sanitized
    0.06
    ernetes
    0.06
    EXPORT
    0.06
     채용
    0.06
    MERCHANTABILITY
    0.06
    ية
    0.06
    생님
    0.06
    itecture
    0.06
    Act Density 0.018%

    No Known Activations