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

    Neuronpedia

    INDEX
    Explanations

    tables with headers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     routed
    0.24
    urface
    0.23
     dyed
    0.20
     obfusc
    0.20
     disposer
    0.20
     surface
    0.19
    izienz
    0.19
    appi
    0.19
     increment
    0.19
     hardened
    0.19
    POSITIVE LOGITS
    音樂
    0.21
     پاورپوینت
    0.19
     موسي
    0.19
    繼續
    0.18
    이란
    0.18
     వివర
    0.18
     بوابة
    0.18
     пояс
    0.18
    ნიშვნ
    0.17
     تھیں
    0.17
    Act Density 0.075%

    No Known Activations