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

    Neuronpedia

    INDEX
    Explanations

    academic/scientific texts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     listView
    -0.08
     quasi
    -0.08
     seri
    -0.07
     youths
    -0.07
    порт
    -0.07
     Ramsey
    -0.07
     Abbott
    -0.07
    在同一
    -0.07
     baptized
    -0.07
     railway
    -0.07
    POSITIVE LOGITS
    関わ
    0.07
    .Generation
    0.07
    网站建设
    0.07
    굴
    0.07
    렜
    0.07
     הפ
    0.07
    אלוה
    0.07
    крыт
    0.06
    ご紹介
    0.06
    お客
    0.06
    Act Density 0.134%

    No Known Activations