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

    Neuronpedia

    INDEX
    Explanations

    Names and locations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     индивиду
    -0.07
    uth
    -0.07
    िद
    -0.07
    abwe
    -0.06
     money
    -0.06
     casing
    -0.06
    inned
    -0.06
    ünde
    -0.06
    ічна
    -0.06
     embeddings
    -0.06
    POSITIVE LOGITS
    .setPrototypeOf
    0.07
    _NONNULL
    0.07
     sağlıklı
    0.07
     uppercase
    0.07
    (currency
    0.07
    nehmer
    0.06
     ngăn
    0.06
    ск
    0.06
     ayud
    0.06
     Fibonacci
    0.06
    Act Density 0.031%

    No Known Activations