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

    Neuronpedia

    INDEX
    Explanations

    mathematical formulas

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     puesto
    -0.08
    -G
    -0.08
     ර
    -0.08
    _FLAGS
    -0.08
    Subtotal
    -0.08
     combinations
    -0.07
     Notre
    -0.07
     Rick
    -0.07
     budget
    -0.07
     eyebrows
    -0.07
    POSITIVE LOGITS
     decomposition
    0.09
     horrible
    0.09
     પ્રમાણે
    0.09
     viejo
    0.08
     pragma
    0.08
     пусть
    0.08
     пикир
    0.08
     preva
    0.08
     fout
    0.08
     prive
    0.08
    Act Density 0.043%

    No Known Activations