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

    Neuronpedia

    INDEX
    Explanations

    surface

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ทำไม
    -0.08
    西红
    -0.07
    빛
    -0.07
     прямо
    -0.07
     Compared
    -0.07
     Sang
    -0.06
     Cement
    -0.06
     sits
    -0.06
    Cook
    -0.06
    に入れ
    -0.06
    POSITIVE LOGITS
    ﻫ
    0.08
     fuzz
    0.07
    争议
    0.07
    isnan
    0.07
    Discuss
    0.07
    _avatar
    0.07
     fulfillment
    0.07
     Discuss
    0.06
    学科
    0.06
    ournal
    0.06
    Act Density 0.004%

    No Known Activations