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

    Neuronpedia

    INDEX
    Explanations

    _to

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    𝓾
    -0.07
    _READONLY
    -0.07
    富豪
    -0.07
    abei
    -0.06
     Scalar
    -0.06
    интерес
    -0.06
    degree
    -0.06
    duced
    -0.06
    /mol
    -0.06
     BU
    -0.06
    POSITIVE LOGITS
    Api
    0.07
     lightweight
    0.07
    锦标赛
    0.07
    .GetProperty
    0.07
     factory
    0.07
     expectations
    0.07
    怀
    0.07
    摏
    0.07
    Rpc
    0.06
     Polymer
    0.06
    Act Density 0.001%

    No Known Activations