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

    Neuronpedia

    INDEX
    Explanations

    Coding and instructions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     intrig
    -0.08
    ړه
    -0.08
    Alliance
    -0.08
    นาย
    -0.08
     hallmark
    -0.08
    ээс
    -0.08
     Affiliate
    -0.08
     болсо
    -0.08
    ่วม
    -0.08
    uum
    -0.08
    POSITIVE LOGITS
     listing
    0.08
    Pagination
    0.07
    Provided
    0.07
    Big
    0.07
     emojis
    0.07
     Big
    0.07
    lem
    0.07
    Bold
    0.07
     bold
    0.07
     equals
    0.07
    Act Density 0.059%

    No Known Activations