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

    Neuronpedia

    INDEX
    Explanations

    ctx followed by Expansion

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    鋼
    0.43
    +\
    0.43
     Тогда
    0.43
    зия
    0.42
    喘
    0.42
     سای
    0.41
    ECTOR
    0.41
    цион
    0.40
     букмекерлар
    0.40
     Поль
    0.40
    POSITIVE LOGITS
     redist
    0.45
     interpre
    0.44
     Encryption
    0.42
     reminis
    0.42
     Accum
    0.42
     easily
    0.41
     Acting
    0.41
     lawns
    0.41
     protop
    0.41
     reinterpret
    0.41
    Act Density 0.007%

    No Known Activations