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

    Neuronpedia

    INDEX
    Explanations

    Press releases/News articles

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Mel
    -0.07
     Associated
    -0.06
    association
    -0.06
     df
    -0.06
    ampoo
    -0.06
     meet
    -0.06
     DL
    -0.06
    Lim
    -0.06
     Josh
    -0.06
    Aside
    -0.06
    POSITIVE LOGITS
     무엇
    0.07
     setUp
    0.07
     جستارهای
    0.06
     شروع
    0.06
     pocházet
    0.06
    .Image
    0.06
     oček
    0.06
    ‌شوند
    0.06
    نان
    0.06
    اورپ
    0.06
    Act Density 0.016%

    No Known Activations