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

    Neuronpedia

    INDEX
    Explanations

    Main choice/option

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    特别
    -0.07
     рядом
    -0.07
    (g
    -0.07
     providedIn
    -0.07
    获得
    -0.06
    _oc
    -0.06
     siguientes
    -0.06
    DY
    -0.06
     undis
    -0.06
     deterior
    -0.06
    POSITIVE LOGITS
     polling
    0.07
    ắp
    0.07
    итуа
    0.07
     Code
    0.06
     goat
    0.06
    نة
    0.06
    -values
    0.06
    -reader
    0.06
    ่ว
    0.06
    če
    0.06
    Act Density 0.110%

    No Known Activations