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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    =(-
    -0.07
    ські
    -0.07
    Managed
    -0.07
    ice
    -0.06
    configure
    -0.06
    igDecimal
    -0.06
    цами
    -0.06
    refixer
    -0.06
    holding
    -0.06
    ran
    -0.06
    POSITIVE LOGITS
     松
    0.07
     Toast
    0.07
     formato
    0.06
     cancellation
    0.06
    >e
    0.06
     MILL
    0.06
     simplest
    0.06
     만들
    0.06
    944
    0.06
     resizable
    0.06
    Act Density 0.106%

    No Known Activations