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

    Neuronpedia

    INDEX
    Explanations

    table dividers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     adiabatically
    0.51
     embolism
    0.46
    ροφο
    0.45
    အစိတ်အပိုင်း
    0.44
    जिस्ट
    0.44
    嫐
    0.43
    ادي
    0.43
    एचओ
    0.43
    ญาต
    0.42
    ühlt
    0.42
    POSITIVE LOGITS
    hline
    0.71
    cline
    0.57
    midrule
    0.54
    0.44
    end
    0.44
     &
    0.42
    ---|
    0.41
    ---+
    0.41
     Sub
    0.40
    }{}
    0.40
    Act Density 0.013%

    No Known Activations