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

    Neuronpedia

    INDEX
    Explanations

    multilingual content

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     McKee
    0.38
    ম্ত
    0.35
    стри
    0.35
    siye
    0.35
     Chill
    0.35
     направления
    0.35
     為
    0.35
     Watering
    0.34
    stri
    0.33
     Hierarchy
    0.33
    POSITIVE LOGITS
     certainly
    0.54
     Certainly
    0.40
     सशस्त्र
    0.38
    antation
    0.37
    Certainly
    0.37
    Default
    0.37
     hond
    0.36
     percep
    0.36
     pertin
    0.35
     পড়েন
    0.35
    Act Density 0.004%

    No Known Activations