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

    Neuronpedia

    INDEX
    Explanations

    generic article text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Rail
    -0.07
     Peter
    -0.07
     пти
    -0.07
     possui
    -0.06
     width
    -0.06
    386
    -0.06
    ado
    -0.06
    Fl
    -0.06
    	session
    -0.06
    412
    -0.06
    POSITIVE LOGITS
     waited
    0.07
    inant
    0.06
    |M
    0.06
     POINTER
    0.06
     podría
    0.06
    what
    0.06
    !!,
    0.06
     intermittent
    0.06
     carbohydrate
    0.06
     GG
    0.06
    Act Density 0.160%

    No Known Activations