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

    Neuronpedia

    INDEX
    Explanations

    aboutwhatmysteryterm

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ()=>{
    1.24
     भती
    1.18
    gloss
    1.13
    چہ
    1.11
    rawberry
    1.10
     چیز
    1.08
    μενο
    1.08
    도
    1.08
     lọc
    1.05
     duly
    1.05
    POSITIVE LOGITS
     estan
    1.30
    ◹
    1.24
    esini
    1.18
    ش
    1.16
    ‍या
    1.15
     outage
    1.12
     altera
    1.12
    ená
    1.09
    شون
    1.08
    elly
    1.08
    Act Density 0.001%

    No Known Activations