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

    Neuronpedia

    INDEX
    Explanations

    giving examples

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     mtoto
    -0.09
     Berdimuhamed
    -0.08
    ుందని
    -0.08
     sidewalks
    -0.08
     Mockito
    -0.08
    ಿಕೆಟ್
    -0.08
     сапраў
    -0.08
     إ
    -0.07
     KOYO
    -0.07
     Onwuka
    -0.07
    POSITIVE LOGITS
    而言
    0.11
     analogy
    0.09
    лу
    0.09
    的话
    0.09
    一下
    0.08
    来说
    0.08
    example
    0.08
    ’am
    0.08
     erh
    0.08
    話
    0.08
    Act Density 0.028%

    No Known Activations