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

    Neuronpedia

    INDEX
    Explanations

    Advertisements

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     мат
    -0.08
    Initially
    -0.07
    行业发展
    -0.07
     البع
    -0.07
    .faceVertexUvs
    -0.07
     Brand
    -0.07
     steadily
    -0.07
    ]|
    -0.07
     brightly
    -0.07
     defaulted
    -0.06
    POSITIVE LOGITS
    按摩
    0.08
     tempting
    0.07
     tłumacz
    0.07
    婴
    0.07
    arding
    0.07
     tác
    0.07
    conte
    0.07
     Особ
    0.07
    让我
    0.06
     judging
    0.06
    Act Density 0.054%

    No Known Activations