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

    Neuronpedia

    INDEX
    Explanations

    Scientific research papers

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    уществ
    -0.08
     대해서
    -0.07
    .Broadcast
    -0.07
     vrou
    -0.07
    走出来
    -0.06
     crackdown
    -0.06
    ימו
    -0.06
    专项资金
    -0.06
    评议
    -0.06
    Broadcast
    -0.06
    POSITIVE LOGITS
    ье
    0.07
    }//
    0.07
     expected
    0.07
     City
    0.07
    /**/*.
    0.07
    异常
    0.06
    ię
    0.06
    "`↵
    0.06
    Entry
    0.06
    �
    0.06
    Act Density 0.355%

    No Known Activations