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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _below
    -0.07
     belongs
    -0.07
    .matmul
    -0.06
     obvious
    -0.06
    ientos
    -0.06
     Chance
    -0.06
     vliv
    -0.06
    pls
    -0.06
    Moves
    -0.06
     Materials
    -0.06
    POSITIVE LOGITS
     Springfield
    0.07
     pra
    0.06
     entityManager
    0.06
     RADIO
    0.06
     příjem
    0.06
    SSI
    0.06
    :test
    0.06
     deport
    0.06
     firstName
    0.06
     Nazi
    0.06
    Act Density 0.024%

    No Known Activations