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

    Neuronpedia

    INDEX
    Explanations

    programming code/errors

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    groupon
    -0.07
     quelque
    -0.07
     постоян
    -0.06
     outrageous
    -0.06
     eBay
    -0.06
     пох
    -0.06
     韓
    -0.06
    洞
    -0.06
    :I
    -0.06
     foll
    -0.06
    POSITIVE LOGITS
    Unsafe
    0.06
     ー
    0.06
     Twe
    0.06
     Newsletter
    0.06
     Rot
    0.06
     Kag
    0.06
    gons
    0.06
     Types
    0.06
    (back
    0.06
    .reshape
    0.06
    Act Density 0.214%

    No Known Activations