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

    Neuronpedia

    INDEX
    Explanations

    non-English languages

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     staffed
    -0.10
     Julie
    -0.10
    /team
    -0.09
     tiket
    -0.09
     Jakarta
    -0.08
    Charlotte
    -0.08
    ート
    -0.08
    ч
    -0.08
     fueled
    -0.08
     propelled
    -0.08
    POSITIVE LOGITS
     checksum
    0.10
    _payload
    0.10
     ciphertext
    0.09
     stuffing
    0.09
     XOR
    0.09
     GAN
    0.09
     modificación
    0.09
    ayload
    0.09
     payload
    0.09
     modificar
    0.09
    Act Density 0.006%

    No Known Activations