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

    Neuronpedia

    INDEX
    Explanations

    technical terms and definitions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     viz
    0.46
     physique
    0.40
     solidity
    0.40
    ened
    0.39
     fand
    0.39
     Physique
    0.38
     naal
    0.38
    ಜ್ಜ
    0.38
    ཿ
    0.38
     aromatic
    0.37
    POSITIVE LOGITS
    🚶
    0.38
     underestimate
    0.38
    🎒
    0.38
    餌
    0.37
    Goss
    0.36
    股份有限公司
    0.36
    UpperCase
    0.36
    ग्विजय
    0.36
    ֔
    0.35
    Շ
    0.35
    Act Density 0.000%

    No Known Activations