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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     прид
    -0.07
     DAG
    -0.07
     unde
    -0.06
     Oversight
    -0.06
    區
    -0.06
    -volume
    -0.06
     προ
    -0.06
    ":↵↵
    -0.06
     كار
    -0.06
    Equivalent
    -0.06
    POSITIVE LOGITS
    션
    0.06
    aycast
    0.06
    getSingleton
    0.06
    ibrary
    0.06
    spNet
    0.06
    ¨
    0.06
    essional
    0.06
    oueur
    0.06
    Host
    0.06
    絶
    0.06
    Act Density 0.063%

    No Known Activations