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

    Neuronpedia

    INDEX
    Explanations

    millions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    深化改革
    -0.08
     Texans
    -0.07
     Baylor
    -0.07
     "/");↵
    -0.07
    恬
    -0.07
    ownt
    -0.07
    Cómo
    -0.07
     Santana
    -0.07
     Trudeau
    -0.07
    oufl
    -0.07
    POSITIVE LOGITS
    Pos
    0.08
     clusters
    0.07
    Vehicle
    0.07
    mı
    0.07
    raised
    0.07
    JA
    0.07
     Above
    0.07
    example
    0.07
    _PADDING
    0.07
    subst
    0.06
    Act Density 0.010%

    No Known Activations