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

    Neuronpedia

    INDEX
    Explanations

    symmetric cryptography

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <h1>
    1.48
    gers
    1.24
    smt
    1.22
     المركزي
    1.15
    clesi
    1.14
    ます
    1.14
    ますが
    1.13
    ʏ
    1.13
    sunday
    1.13
     sinar
    1.11
    POSITIVE LOGITS
     confided
    1.84
    م
    1.62
    ில்
    1.59
     revoke
    1.57
     insulted
    1.57
    м
    1.49
     tabled
    1.49
     playfully
    1.47
    𝘸
    1.47
     forgo
    1.46
    Act Density 0.000%

    No Known Activations