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

    Neuronpedia

    INDEX
    Explanations

    )

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Ships
    -0.07
    ẻ
    -0.06
    ield
    -0.06
    ��
    -0.06
    зація
    -0.06
    их
    -0.06
     prisons
    -0.06
    dealer
    -0.06
     classifiers
    -0.06
     vyšší
    -0.06
    POSITIVE LOGITS
    ,:]
    0.07
     Sect
    0.07
    Scalar
    0.06
    lası
    0.06
     gonna
    0.06
     �
    0.06
    ทางการ
    0.06
     курс
    0.06
    .hxx
    0.06
    地说
    0.06
    Act Density 0.002%

    No Known Activations