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

    Neuronpedia

    INDEX
    Explanations

    security and cryptography

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     compromise
    0.43
    frast
    0.40
     compromises
    0.40
     Chiropractic
    0.39
     کیونکہ
    0.39
     Geological
    0.38
    endis
    0.38
    헛
    0.38
    propertyPath
    0.38
     presumption
    0.37
    POSITIVE LOGITS
    ксе
    0.38
    нений
    0.37
     grupos
    0.37
    sham
    0.37
     sham
    0.36
     desempe
    0.36
     গোষ্ঠ
    0.36
     CRY
    0.36
     stuffed
    0.35
    crypto
    0.35
    Act Density 0.005%

    No Known Activations