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

    Neuronpedia

    INDEX
    Explanations

    hashing algorithms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    🛌
    0.46
    gown
    0.45
    徬
    0.45
     клавиа
    0.45
     apporter
    0.45
    ローブ
    0.44
    knie
    0.43
    匏
    0.42
    اليه
    0.42
     বাহুল্য
    0.42
    POSITIVE LOGITS
     hash
    1.98
     hashing
    1.80
     hashes
    1.77
    Hash
    1.69
    hash
    1.62
     Hash
    1.60
     hashed
    1.51
     SHA
    1.48
    Hashing
    1.47
     checksum
    1.46
    Act Density 0.081%

    No Known Activations