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

    Neuronpedia

    INDEX
    Explanations

    artificial intelligence

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     privileges
    -0.06
     XI
    -0.06
     ways
    -0.06
     site
    -0.06
     JOIN
    -0.06
     casino
    -0.06
     camino
    -0.06
    ies
    -0.06
     eso
    -0.06
     ling
    -0.06
    POSITIVE LOGITS
    rounded
    0.07
     starred
    0.07
     technician
    0.06
    entlich
    0.06
     stocked
    0.06
    oubles
    0.06
     اینکه
    0.06
    �
    0.06
    を見る
    0.06
    кт
    0.06
    Act Density 0.005%

    No Known Activations