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

    Neuronpedia

    INDEX
    Explanations

    Diverse broad topics

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     enacted
    -0.08
     Dor
    -0.07
     sellers
    -0.07
    拤
    -0.07
    难以
    -0.06
    -generic
    -0.06
    .epam
    -0.06
     doomed
    -0.06
     expects
    -0.06
     Puerto
    -0.06
    POSITIVE LOGITS
    					
↵
    0.07
    定律
    0.07
    -css
    0.07
    休息
    0.07
    加分
    0.07
    accur
    0.07
    意見
    0.06
     分
    0.06
     sockaddr
    0.06
    ￥
    0.06
    Act Density 0.003%

    No Known Activations