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

    Neuronpedia

    INDEX
    Explanations

    Technical writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ainless
    -0.07
     полот
    -0.07
    ("(%
    -0.07
     최대
    -0.06
    宗
    -0.06
     Eleanor
    -0.06
    _HOR
    -0.06
    i�
    -0.06
    öl
    -0.06
    TestFixture
    -0.06
    POSITIVE LOGITS
     vinc
    0.07
     Error
    0.07
     somew
    0.07
    597
    0.06
    ks
    0.06
     
↵
↵
    0.06
    .|
    0.06
     Good
    0.06
    rý
    0.06
    locks
    0.06
    Act Density 0.000%

    No Known Activations