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

    Neuronpedia

    INDEX
    Explanations

    record

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     parach
    -0.09
     Laurent
    -0.08
    ξη
    -0.08
     bước
    -0.08
    �
    -0.08
    Branches
    -0.08
     perché
    -0.08
     emiss
    -0.08
    步骤
    -0.08
     palpable
    -0.07
    POSITIVE LOGITS
    ドラ
    0.09
     premiere
    0.09
     Premiere
    0.09
     фильмы
    0.09
     television
    0.09
    予約
    0.08
    録
    0.08
     predictive
    0.08
     архив
    0.08
     grab
    0.08
    Act Density 0.012%

    No Known Activations