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

    Neuronpedia

    INDEX
    Explanations

    sprained

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _WRAPPER
    -0.08
     Ну
    -0.07
    .handle
    -0.07
    _stderr
    -0.06
     Ок
    -0.06
    nov
    -0.06
     Rx
    -0.06
    ovaný
    -0.06
     atte
    -0.06
    .Geometry
    -0.06
    POSITIVE LOGITS
     cookie
    0.07
    악
    0.06
     dok
    0.06
     overturned
    0.06
    413
    0.06
    436
    0.06
    ��
    0.06
    grund
    0.06
     weld
    0.06
     ngũ
    0.06
    Act Density 0.012%

    No Known Activations