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

    Neuronpedia

    INDEX
    Explanations

    numbers with three

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ござい
    0.48
    ্কর
    0.46
    GONDOR
    0.45
     réduit
    0.45
    ोतरी
    0.44
     سمجھتے
    0.43
    ্ঠ
    0.41
    감이
    0.41
     ነ
    0.41
     hän
    0.41
    POSITIVE LOGITS
    rd
    1.27
    rds
    0.74
    3
    0.72
    d
    0.70
    quarters
    0.69
     rd
    0.68
     तलाक
    0.61
     cheers
    0.59
    fourths
    0.58
    k
    0.56
    Act Density 0.150%

    No Known Activations