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

    Neuronpedia

    INDEX
    Explanations

    inventions, discoveries

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    anson
    -0.07
    ेण
    -0.07
    rp
    -0.06
     обо
    -0.06
    ibbon
    -0.06
    ука
    -0.06
     канди
    -0.06
     neuronal
    -0.06
     categoryId
    -0.06
    디시
    -0.06
    POSITIVE LOGITS
     即
    0.07
    Mem
    0.07
     RAM
    0.06
    -eff
    0.06
    ")).
    0.06
     Mem
    0.06
     эп
    0.06
     Soviets
    0.06
     Wing
    0.06
     ↵  ↵
    0.06
    Act Density 0.044%

    No Known Activations