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

    Neuronpedia

    INDEX
    Explanations

    test

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     cà
    -0.07
     absence
    -0.07
    습니다
    -0.07
     acompaña
    -0.07
    무
    -0.07
    承接
    -0.07
    حاد
    -0.06
    fé
    -0.06
    葡
    -0.06
    侈
    -0.06
    POSITIVE LOGITS
    ︕
    0.07
     особенно
    0.07
     willing
    0.07
     contemplated
    0.07
    Organization
    0.07
     deserted
    0.07
     formulated
    0.06
    .Authentication
    0.06
    .githubusercontent
    0.06
    asma
    0.06
    Act Density 0.006%

    No Known Activations