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

    Neuronpedia

    INDEX
    Explanations

    Darwin

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    наслідок
    -0.07
    емати
    -0.07
     CHE
    -0.07
    пр
    -0.06
     accent
    -0.06
     питань
    -0.06
     Elena
    -0.06
    일에
    -0.06
    ือข
    -0.06
    وله
    -0.06
    POSITIVE LOGITS
     Darwin
    0.13
     darling
    0.07
     woke
    0.07
     lub
    0.07
    think
    0.07
    /bin
    0.07
    sid
    0.07
    .client
    0.07
     dar
    0.07
     luận
    0.07
    Act Density 0.002%

    No Known Activations