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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Gather
    -0.06
     maliyet
    -0.06
     toplumsal
    -0.06
    kop
    -0.06
    mvc
    -0.06
     McK
    -0.06
    _click
    -0.06
    洪
    -0.05
     Hibernate
    -0.05
    Ruby
    -0.05
    POSITIVE LOGITS
    イ
    0.07
    的是
    0.07
    케이
    0.06
     kênh
    0.06
     deleteUser
    0.06
    oodle
    0.06
     nay
    0.06
    _customer
    0.06
     Il
    0.06
    .forEach
    0.06
    Act Density 0.249%

    No Known Activations