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

    Neuronpedia

    INDEX
    Explanations

    non

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     summarize
    -0.08
     AS
    -0.07
     minut
    -0.07
     minX
    -0.06
     سال
    -0.06
    τίου
    -0.06
     route
    -0.06
    ज
    -0.06
    =text
    -0.06
    osal
    -0.06
    POSITIVE LOGITS
     ẩm
    0.07
     insulting
    0.07
    <!
    0.07
     Vancouver
    0.06
    íd
    0.06
    :left
    0.06
    ื้
    0.06
    sole
    0.06
     güçlü
    0.06
    ılmış
    0.06
    Act Density 0.011%

    No Known Activations