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

    Neuronpedia

    INDEX
    Explanations

    word frequency and counts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ম
    0.95
     संपत्ति
    0.95
    agers
    0.93
    ח
    0.90
    ك
    0.89
    सी
    0.89
     a
    0.87
    एम
    0.86
     सामग्री
    0.86
     आंकड़ों
    0.85
    POSITIVE LOGITS
    чи
    0.96
     powied
    0.94
    <0x80>
    0.92
    します
    0.90
    し
    0.85
    ου
    0.84
     prennent
    0.84
    "></
    0.82
    っている
    0.79
    ون
    0.78
    Act Density 0.147%

    No Known Activations