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

    Neuronpedia

    INDEX
    Explanations

    list item starters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     воск
    0.29
    getTime
    0.29
    anaa
    0.29
    国务
    0.28
    getPopulation
    0.28
    偃
    0.28
    ượ
    0.28
    UCI
    0.27
    Isaiah
    0.27
    ೆಗೆ
    0.27
    POSITIVE LOGITS
     cach
    0.33
     Mut
    0.30
     aliphatic
    0.29
     fragment
    0.29
     string
    0.29
     transport
    0.29
     dz
    0.28
     gluon
    0.28
     dark
    0.28
     ara
    0.28
    Act Density 0.003%

    No Known Activations