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

    Neuronpedia

    INDEX
    Explanations

    named entity recognition

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     name
    1.24
     Namen
    1.20
    name
    1.17
     Name
    1.16
     naming
    1.11
     names
    1.02
     Names
    1.01
    NAME
    1.01
    名稱
    0.96
    names
    0.94
    POSITIVE LOGITS
     loại
    0.86
     документів
    0.82
    檄
    0.80
    方法的
    0.80
     внимания
    0.79
     Método
    0.79
     kroz
    0.79
     तरीकों
    0.78
     émissions
    0.78
     tanta
    0.78
    Act Density 0.036%

    No Known Activations