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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    fmt
    -0.07
    쌔
    -0.07
    射
    -0.07
     Nuclear
    -0.07
    🇫
    -0.07
    �
    -0.07
    /store
    -0.07
    赠
    -0.07
    ỉ
    -0.07
     gunshot
    -0.06
    POSITIVE LOGITS
     EVEN
    0.07
    ervals
    0.07
     fatalities
    0.07
    erville
    0.07
     canyon
    0.07
    viewController
    0.07
     kilometres
    0.07
     الغربية
    0.07
     classifications
    0.07
     viewController
    0.07
    Act Density 0.000%

    No Known Activations