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

    Neuronpedia

    INDEX
    Explanations

    ni

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     roast
    -0.07
     comet
    -0.07
    ひ
    -0.07
    🌹
    -0.07
     พ
    -0.07
    נייר
    -0.07
    칭
    -0.07
    শ
    -0.07
    otos
    -0.07
    情人
    -0.07
    POSITIVE LOGITS
    NY
    0.07
    -keys
    0.07
     تعال
    0.07
     Kle
    0.07
    懒
    0.07
    /nginx
    0.07
     Handler
    0.06
     queries
    0.06
    但它
    0.06
    0.06
    Act Density 0.002%

    No Known Activations