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

    Neuronpedia

    INDEX
    Explanations

    game?

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    шие
    1.13
     mga
    1.13
    вшие
    1.07
     случаях
    1.06
    গুলি
    1.05
     ones
    1.05
    ವರಿಗೆ
    1.04
     গুলো
    1.04
    们
    1.03
     якія
    1.03
    POSITIVE LOGITS
    和一个
    1.48
     somewhere
    1.32
     someone
    1.17
     somebody
    1.11
     whose
    1.10
     someplace
    1.05
     called
    1.02
     unrelated
    1.02
     like
    1.00
     thats
    0.98
    Act Density 0.723%

    No Known Activations