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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     realism
    -0.08
    .Control
    -0.07
     Quincy
    -0.07
    oracle
    -0.07
     getopt
    -0.07
    	sql
    -0.07
    .getText
    -0.07
    的知识
    -0.07
    –and
    -0.07
     redis
    -0.07
    POSITIVE LOGITS
    吽
    0.08
    Б
    0.07
    '.↵↵
    0.07
     조
    0.07
     bất
    0.07
    נן
    0.07
     услуги
    0.07
    蔷
    0.07
    批复
    0.06
     rtn
    0.06
    Act Density 0.083%

    No Known Activations