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

    Neuronpedia

    INDEX
    Explanations

    character classes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Clemson
    -0.08
     Belarus
    -0.08
     Knicks
    -0.08
    ighting
    -0.08
     Bezos
    -0.08
    ensus
    -0.08
     Basketball
    -0.08
     Belize
    -0.08
     Syndrome
    -0.07
     Latvia
    -0.07
    POSITIVE LOGITS
     گروه
    0.09
    范围
    0.08
    یرہ
    0.08
     collections
    0.08
     curated
    0.08
     ranges
    0.08
     déan
    0.08
     router
    0.08
     RANGE
    0.08
    _RANGE
    0.08
    Act Density 0.007%

    No Known Activations