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

    Neuronpedia

    INDEX
    Explanations

    range between two values

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ตรฐาน
    1.29
     overwhelm
    1.24
    damn
    1.22
     imprison
    1.20
    க
    1.19
     demise
    1.18
     scena
    1.18
    intrusion
    1.16
     vertices
    1.16
     কাছে
    1.16
    POSITIVE LOGITS
     الاقوامی
    1.67
     المللی
    1.46
     אם
    1.41
    েও
    1.41
    tanto
    1.30
     између
    1.28
    лари
    1.27
     ayr
    1.21
    اً
    1.19
    өлү
    1.11
    Act Density 0.054%

    No Known Activations