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

    Neuronpedia

    INDEX
    Explanations

    layer

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     якій
    -0.07
     sale
    -0.06
     girls
    -0.06
    .DESC
    -0.06
    ²
    -0.06
    이다
    -0.06
    ��
    -0.06
     Sale
    -0.06
     brief
    -0.06
    .tt
    -0.06
    POSITIVE LOGITS
     viewController
    0.06
    (expect
    0.06
    _normalize
    0.06
    pass
    0.06
     Newtonsoft
    0.06
    込
    0.06
    (forKey
    0.06
    奈
    0.06
     багат
    0.06
    ากล
    0.06
    Act Density 0.210%

    No Known Activations