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

    Neuronpedia

    INDEX
    Explanations

    =

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Beaver
    -0.07
     Мик
    -0.07
     kullanılan
    -0.06
    роиз
    -0.06
    Flash
    -0.06
     fileName
    -0.06
    tak
    -0.06
    iloc
    -0.06
    Fit
    -0.06
    ovanou
    -0.06
    POSITIVE LOGITS
    according
    0.07
     майже
    0.07
    uddle
    0.07
    ektir
    0.06
     ################
    0.06
    \Routing
    0.06
    acie
    0.06
    (input
    0.06
     ندار
    0.06
    检查
    0.06
    Act Density 0.000%

    No Known Activations