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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (mod
    -0.06
    ्कर
    -0.06
     roomId
    -0.06
     Levin
    -0.06
     atd
    -0.06
    寺
    -0.06
    Tit
    -0.06
    Height
    -0.06
    every
    -0.06
     ти
    -0.06
    POSITIVE LOGITS
    [:,
    0.06
     quam
    0.06
    *size
    0.06
    ？”
    0.06
    ocommerce
    0.06
     coma
    0.06
    ाज
    0.06
    --------------
    0.06
     redund
    0.06
    [arr
    0.06
    Act Density 0.098%

    No Known Activations