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

    Neuronpedia

    INDEX
    Explanations

    non-english words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Finder
    0.41
     recomend
    0.41
    பார
    0.40
    Margin
    0.39
     Sob
    0.38
    మారు
    0.38
     Promo
    0.38
    孝
    0.37
     Recommendation
    0.37
     outlier
    0.37
    POSITIVE LOGITS
     രൂപ
    0.42
    aia
    0.39
    decimals
    0.37
     কালিক
    0.37
    ciaux
    0.36
    dek
    0.35
    আল
    0.35
     कार्ट
    0.35
    lä
    0.35
     এলো
    0.35
    Act Density 0.000%

    No Known Activations