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

    Neuronpedia

    INDEX
    Explanations

    class-dump copyright headers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    200
    -0.06
    moduleId
    -0.06
     nurse
    -0.06
    .....
    -0.06
    qrstuvwxyz
    -0.06
    )">↵
    -0.06
    weep
    -0.06
     presenter
    -0.06
    很多
    -0.06
     mAdapter
    -0.06
    POSITIVE LOGITS
    �
    0.08
     harming
    0.07
    attering
    0.06
    own
    0.06
    /display
    0.06
    بات
    0.06
     그를
    0.06
    OWER
    0.06
     arm
    0.06
     Alter
    0.06
    Act Density 0.000%

    No Known Activations