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

    Neuronpedia

    INDEX
    Explanations

    .factory

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    halten
    -0.06
    xd
    -0.06
    iven
    -0.06
    eldo
    -0.06
    uell
    -0.06
    BM
    -0.06
     olds
    -0.06
    pped
    -0.06
     primes
    -0.06
    yen
    -0.06
    POSITIVE LOGITS
    .factory
    0.10
    Survey
    0.07
    cuda
    0.07
    Study
    0.07
    Factory
    0.07
    ("/");↵
    0.07
     Achievement
    0.06
     restore
    0.06
     "/";↵
    0.06
    Before
    0.06
    Act Density 0.001%

    No Known Activations