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

    Neuronpedia

    INDEX
    Explanations

    pass

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     lud
    -0.08
     supplemental
    -0.08
    quart
    -0.08
     laughter
    -0.07
     enkel
    -0.07
    مند
    -0.07
    相信
    -0.07
     portefeuille
    -0.07
     mindset
    -0.07
     bouteille
    -0.07
    POSITIVE LOGITS
     noon
    0.09
     Noon
    0.08
     दुस
    0.08
     지나
    0.08
     जाण
    0.08
     объ
    0.08
    ivate
    0.07
     komt
    0.07
     landmarks
    0.07
     Callback
    0.07
    Act Density 0.008%

    No Known Activations