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

    Neuronpedia

    INDEX
    Explanations

    temporal prepositions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     perennial
    -0.08
     Wagner
    -0.07
     Moral
    -0.07
     Buckingham
    -0.07
     Reagan
    -0.06
     Knicks
    -0.06
     проекту
    -0.06
    :X
    -0.06
     ankle
    -0.06
    arning
    -0.06
    POSITIVE LOGITS
    与
    0.07
     与
    0.06
    とい
    0.06
    _re
    0.06
     FileType
    0.06
     Experiment
    0.06
     配
    0.06
     İzmir
    0.06
    _Impl
    0.06
     velik
    0.06
    Act Density 0.066%

    No Known Activations