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
     округ
    -0.07
    gu
    -0.07
    936
    -0.06
     охорони
    -0.06
    -container
    -0.06
     overflow
    -0.06
     lodge
    -0.06
    يث
    -0.06
    ाण
    -0.06
    (provider
    -0.06
    POSITIVE LOGITS
     Lup
    0.07
     emphasizing
    0.06
    \":{\"
    0.06
     Competitive
    0.06
     tran
    0.06
     basketball
    0.06
     Functions
    0.06
     vastly
    0.06
    ％
    0.06
    *y
    0.06
    Act Density 0.000%

    No Known Activations