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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     accelerate
    -0.07
    έρα
    -0.06
    _IDS
    -0.06
    .spy
    -0.06
     laugh
    -0.06
     На
    -0.06
    .byId
    -0.06
    _cate
    -0.06
     Jas
    -0.06
    โร
    -0.06
    POSITIVE LOGITS
     getResource
    0.07
     октября
    0.06
     Конститу
    0.06
     فرمود
    0.06
    docker
    0.06
    _machine
    0.06
     Parameter
    0.06
     ___
    0.06
     Mutation
    0.06
     llvm
    0.06
    Act Density 0.000%

    No Known Activations