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

    Neuronpedia

    INDEX
    Explanations

    ons

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     two
    -0.08
     Related
    -0.07
     three
    -0.06
    Two
    -0.06
    three
    -0.06
     một
    -0.06
    Three
    -0.06
     otra
    -0.06
     our
    -0.06
    Receipt
    -0.06
    POSITIVE LOGITS
     harmful
    0.07
    .speed
    0.07
     Επ
    0.07
    perhaps
    0.07
     setTitleColor
    0.06
     περι
    0.06
    (redis
    0.06
    िकट
    0.06
    >&
    0.06
     Dustin
    0.06
    Act Density 0.081%

    No Known Activations