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

    Neuronpedia

    INDEX
    Explanations

    web server bind

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    एनएल
    0.41
     extravaganza
    0.38
    ನನ್ನು
    0.36
    واعد
    0.34
    اردوش
    0.34
    ल्क
    0.33
    开头
    0.33
     Boca
    0.33
    صفوف
    0.33
     antidepress
    0.32
    POSITIVE LOGITS
     tâ
    0.40
     pab
    0.39
     repe
    0.34
    platinum
    0.34
     Mete
    0.34
     Jacks
    0.34
     foreseeable
    0.33
    ᱹ
    0.32
     Gro
    0.32
     ca
    0.32
    Act Density 0.001%

    No Known Activations