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

    Neuronpedia

    INDEX
    Explanations

    Code differentiation/importing

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    𬘩
    -0.07
    淨
    -0.07
     shipments
    -0.07
    屋子
    -0.07
    aning
    -0.07
    새
    -0.07
     Corner
    -0.07
     Collabor
    -0.07
    inction
    -0.07
    的话语
    -0.07
    POSITIVE LOGITS
    curso
    0.08
    pow
    0.07
    posal
    0.07
    赟
    0.07
    )*(
    0.07
    _REFERENCE
    0.07
    前所未
    0.07
    工作岗位
    0.07
     Baz
    0.07
     요구
    0.07
    Act Density 0.007%

    No Known Activations