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

    Neuronpedia

    INDEX
    Explanations

    code definitions and new creations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     fulfills
    0.45
     histologic
    0.45
    硝
    0.45
     суть
    0.44
     brews
    0.43
     boils
    0.43
     secures
    0.43
     overwritten
    0.42
    StartAddress
    0.42
    краё
    0.42
    POSITIVE LOGITS
     المزيد
    0.45
    ducers
    0.39
     قبل
    0.38
    وا
    0.38
     Unternehmen
    0.37
     আগে
    0.37
     APP
    0.37
    w
    0.37
     Angst
    0.37
     App
    0.36
    Act Density 0.001%

    No Known Activations