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

    Neuronpedia

    INDEX
    Explanations

    equals symbol

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     urlString
    -0.07
     Pract
    -0.06
    RowAt
    -0.06
    hammad
    -0.06
    Units
    -0.06
     segregated
    -0.06
    aida
    -0.06
    층
    -0.06
     /*!
    -0.06
    achi
    -0.06
    POSITIVE LOGITS
    =
    0.06
     cellular
    0.06
    =l
    0.06
    =sys
    0.06
     riff
    0.06
    =${
    0.06
    -transitional
    0.06
     demanded
    0.06
    Không
    0.06
    /frame
    0.06
    Act Density 0.005%

    No Known Activations