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

    Neuronpedia

    INDEX
    Explanations

    programming

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     shouting
    -0.07
    fox
    -0.07
    简单
    -0.06
     jdbcTemplate
    -0.06
    _response
    -0.06
     τους
    -0.06
     bully
    -0.06
     Quý
    -0.06
    挑
    -0.06
     ua
    -0.06
    POSITIVE LOGITS
     differed
    0.07
    ，使
    0.07
    ılacak
    0.07
     Among
    0.07
     belonged
    0.06
    uccess
    0.06
     Isaiah
    0.06
    {\"
    0.06
     ''
    0.06
     attributed
    0.06
    Act Density 0.025%

    No Known Activations