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

    Neuronpedia

    INDEX
    Explanations

    website content

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    <Animator
    -0.07
    Mocks
    -0.07
    Clinton
    -0.07
    的竞争
    -0.07
     reaching
    -0.06
     Vale
    -0.06
    _product
    -0.06
    .spotify
    -0.06
    :Int
    -0.06
    アクセ
    -0.06
    POSITIVE LOGITS
     las
    0.08
    把这个
    0.07
     kitt
    0.07
    حرية
    0.07
    Verb
    0.07
    ಲ
    0.06
     ф
    0.06
    뉴스
    0.06
     ******************************************************************************↵
    0.06
     sparse
    0.06
    Act Density 0.010%

    No Known Activations