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

    Neuronpedia

    INDEX
    Explanations

    ください

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _patient
    -0.07
    平方公里
    -0.07
    共
    -0.07
     feeds
    -0.07
    出
    -0.06
     hoặc
    -0.06
    ufs
    -0.06
     monuments
    -0.06
    DTO
    -0.06
    狂
    -0.06
    POSITIVE LOGITS
     también
    0.06
    -founded
    0.06
    라피
    0.06
    ampa
    0.06
    uppercase
    0.06
    retim
    0.06
     airflow
    0.06
    umbing
    0.06
     yacc
    0.06
    GD
    0.06
    Act Density 0.013%

    No Known Activations