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

    Neuronpedia

    INDEX
    Explanations

    assert

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ceremonies
    -0.07
     schedules
    -0.06
    红
    -0.06
    exampleInputEmail
    -0.06
    .products
    -0.06
     gender
    -0.06
     webpage
    -0.06
     Davies
    -0.06
     gearbox
    -0.06
     james
    -0.06
    POSITIVE LOGITS
    .assert
    0.10
     فرض
    0.08
    bstract
    0.07
    assert
    0.07
     assert
    0.07
     =>'
    0.07
     ＞
    0.07
    jections
    0.07
     afirm
    0.07
    ATT
    0.07
    Act Density 0.007%

    No Known Activations