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

    Neuronpedia

    INDEX
    Explanations

    submission and abuse

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Ⴖ
    0.50
    ஸ்த
    0.50
    ाइल
    0.49
    ೮
    0.49
    selfobj
    0.47
    と考えられる
    0.46
    lenme
    0.46
    ಢ
    0.46
    hatiti
    0.45
    捚
    0.45
    POSITIVE LOGITS
     processor
    0.52
    :
    0.47
     processing
    0.45
     repository
    0.44
     supermarket
    0.43
     shopper
    0.43
    Compute
    0.42
     xử
    0.42
    <0x87>
    0.41
     convenience
    0.41
    Act Density 0.003%

    No Known Activations