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

    Neuronpedia

    INDEX
    Explanations

    communication

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ]%
    -0.07
    Bush
    -0.07
     Casual
    -0.07
     brush
    -0.06
    cuda
    -0.06
     Nep
    -0.06
    .default
    -0.06
     calam
    -0.06
    -Muslim
    -0.06
     external
    -0.06
    POSITIVE LOGITS
    phthalm
    0.06
     Hub
    0.06
    発表
    0.06
    ChildIndex
    0.06
    译
    0.06
     InternalEnumerator
    0.06
     серд
    0.06
    irq
    0.06
     jsonString
    0.06
     addItem
    0.06
    Act Density 0.099%

    No Known Activations