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

    Neuronpedia

    INDEX
    Explanations

    directory

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     severity
    -0.09
     copper
    -0.07
     यद
    -0.06
     polish
    -0.06
    nam
    -0.06
    -neutral
    -0.06
    (Utils
    -0.06
    �
    -0.06
     overcoming
    -0.06
     불
    -0.06
    POSITIVE LOGITS
     arist
    0.07
    etsy
    0.07
    Middle
    0.07
    330
    0.06
     crit
    0.06
    оюз
    0.06
    sunuz
    0.06
    ár
    0.06
    limit
    0.06
     sahiptir
    0.06
    Act Density 0.001%

    No Known Activations