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

    Neuronpedia

    INDEX
    Explanations

    criteria for

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     erwarten
    0.43
    Michel
    0.42
    につ
    0.40
    冶
    0.39
     ধ্ব
    0.39
     сми
    0.39
    แน่นอน
    0.38
     =>
    0.37
    ന്ധി
    0.37
     öffentliche
    0.37
    POSITIVE LOGITS
    ारों
    0.41
     pract
    0.41
    pract
    0.40
    பாட
    0.40
     beg
    0.40
    चित्र
    0.39
     disert
    0.38
     predicting
    0.37
    தர்
    0.37
    wash
    0.37
    Act Density 0.000%

    No Known Activations