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
    jax
    -0.07
     Πο
    -0.07
    -archive
    -0.06
     機
    -0.06
    Love
    -0.06
     Vote
    -0.06
     tests
    -0.06
     Borrow
    -0.06
     Eighth
    -0.06
     خودرو
    -0.06
    POSITIVE LOGITS
    有限
    0.07
    (unsigned
    0.06
     الاست
    0.06
    [selected
    0.06
    ্�
    0.06
    regn
    0.06
    legen
    0.06
     zag
    0.06
     выдел
    0.06
    .WEST
    0.06
    Act Density 0.013%

    No Known Activations