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

    Neuronpedia

    INDEX
    Explanations

    biographies

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    peration
    -0.07
    эм
    -0.06
     zobowią
    -0.06
     Memphis
    -0.06
     memor
    -0.06
     Angela
    -0.06
    cesso
    -0.06
     Cape
    -0.06
     IMP
    -0.06
     العب
    -0.06
    POSITIVE LOGITS
    caught
    0.08
    看看
    0.07
    &);↵↵
    0.07
    受不了
    0.07
    լ
    0.07
    在意
    0.07
    ocular
    0.06
    units
    0.06
     drifting
    0.06
    .WindowManager
    0.06
    Act Density 0.052%

    No Known Activations