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

    Neuronpedia

    INDEX
    Explanations

    overall metrics and statistics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ு
    2.22
    ে
    2.18
    en
    2.08
    े
    2.08
    ال
    2.00
    eV
    1.89
    𝑒
    1.83
    Б
    1.81
    ю
    1.79
    Ƙ
    1.78
    POSITIVE LOGITS
    ্ট
    2.06
    IgnoreCase
    2.03
    ்ப்ப
    1.91
     मिलाकर
    1.89
     allegiance
    1.78
     strapping
    1.78
    بخ
    1.77
     podendo
    1.76
     tain
    1.73
    곽
    1.73
    Act Density 0.082%

    No Known Activations