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

    Neuronpedia

    INDEX
    Explanations

    languages, recipes, ETF, manager

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     effectuées
    0.52
    各类
    0.48
    ignée
    0.47
     منظور
    0.46
    额外的
    0.45
     gigantes
    0.44
     postoje
    0.44
     ظهر
    0.43
     لمن
    0.43
    𝙧
    0.43
    POSITIVE LOGITS
    نا
    0.50
    Student
    0.47
     Pastel
    0.47
     Student
    0.46
     रखता
    0.46
     student
    0.45
     Newbury
    0.44
    DEL
    0.44
    بر
    0.44
    lsch
    0.44
    Act Density 0.000%

    No Known Activations