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

    Neuronpedia

    INDEX
    Explanations

    documents

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     mav
    -0.08
     الفندق
    -0.07
     своим
    -0.07
     гид
    -0.07
    irmingham
    -0.07
     vaccines
    -0.07
     faculties
    -0.07
     dní
    -0.07
     kol
    -0.07
     своими
    -0.07
    POSITIVE LOGITS
     filings
    0.10
    公開
    0.10
    公开
    0.10
     openbare
    0.09
     públic
    0.09
     transcript
    0.09
     revealed
    0.09
    透露
    0.09
     pública
    0.09
     disclosed
    0.08
    Act Density 0.073%

    No Known Activations