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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     kitten
    -0.06
    atology
    -0.06
     saúde
    -0.06
     warned
    -0.06
     ladies
    -0.06
    _EXPRESSION
    -0.06
     เก
    -0.06
    šší
    -0.06
    .onCreate
    -0.06
    Sm
    -0.06
    POSITIVE LOGITS
    acers
    0.07
    !“
    0.07
    olynomial
    0.06
     carbohydrate
    0.06
    utral
    0.06
    yclic
    0.06
    ्ट
    0.06
    any
    0.06
    Clar
    0.06
    ANY
    0.06
    Act Density 0.058%

    No Known Activations