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

    Neuronpedia

    INDEX
    Explanations

    considering "the", "be"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    みよう
    -1.26
    ござい
    -1.21
     verst
    -1.20
    これも
    -1.15
    がない
    -1.13
    фера
    -1.13
     mengembangkan
    -1.12
    臵
    -1.12
     nytt
    -1.10
    惴
    -1.10
    POSITIVE LOGITS
     powied
    1.22
     pensez
    1.20
     recientes
    1.20
    之际
    1.19
     która
    1.18
     ಮತ್ತು
    1.16
    .
    1.15
     mój
    1.13
    高达
    1.12
     کنه
    1.12
    Act Density 0.351%

    No Known Activations