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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    achi
    -0.07
    的画面
    -0.07
    itioner
    -0.07
    'd
    -0.07
    乌克兰
    -0.06
     Dabei
    -0.06
     pricey
    -0.06
    镶嵌
    -0.06
    第六届
    -0.06
    /y
    -0.06
    POSITIVE LOGITS
     maneuver
    0.08
    chrom
    0.07
     stringByAppending
    0.07
    :request
    0.07
    (language
    0.06
     Muj
    0.06
    طيع
    0.06
     yürüt
    0.06
     noises
    0.06
    -div
    0.06
    Act Density 0.030%

    No Known Activations