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

    Neuronpedia

    INDEX
    Explanations

    literature

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     doen
    -0.07
    、どう
    -0.06
     خدمات
    -0.06
    =d
    -0.06
    oid
    -0.06
     acces
    -0.06
    emin
    -0.06
     whistlebl
    -0.06
    _,↵
    -0.06
    },
↵
    -0.06
    POSITIVE LOGITS
    .pg
    0.07
     fauna
    0.07
     хол
    0.07
    tere
    0.07
     И
    0.07
     венти
    0.06
    лами
    0.06
     Tarih
    0.06
     incorporates
    0.06
     downtime
    0.06
    Act Density 0.001%

    No Known Activations