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

    Neuronpedia

    INDEX
    Explanations

    names

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    漻
    -0.07
    	cerr
    -0.07
    Jerry
    -0.07
    モノ
    -0.07
    .navigationController
    -0.07
    ullen
    -0.07
    铷
    -0.07
     cross
    -0.07
     млн
    -0.07
    ければ
    -0.07
    POSITIVE LOGITS
    (cam
    0.07
    TestFixture
    0.07
    [:]
    0.07
    ize
    0.06
    _game
    0.06
     standardized
    0.06
    hape
    0.06
     rhyme
    0.06
     }}↵↵
    0.06
    ("↵
    0.06
    Act Density 0.067%

    No Known Activations