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

    Neuronpedia

    INDEX
    Explanations

    ```xml

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    鲛
    0.79
     बनेगा
    0.78
     பக்கம்
    0.78
    قق
    0.78
    экс
    0.77
    istas
    0.76
    जबकि
    0.76
    atas
    0.76
    പടി
    0.76
    Dust
    0.75
    POSITIVE LOGITS
     dearly
    0.88
    敬
    0.81
     μη
    0.78
    ανα
    0.76
     unconditionally
    0.75
    στη
    0.75
    營
    0.75
    singer
    0.74
     sayang
    0.73
     eukaryotes
    0.72
    Act Density 0.004%

    No Known Activations