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

    Neuronpedia

    INDEX
    Explanations

    suma or arranged

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Елена
    0.43
    Decedent
    0.43
    гази
    0.43
    Eggs
    0.43
    ikt
    0.42
     Олександр
    0.42
     따른
    0.41
    scape
    0.41
     กัน
    0.41
     стекло
    0.41
    POSITIVE LOGITS
    ли
    0.55
    x
    0.52
     i
    0.46
    бра
    0.45
     m
    0.45
    怨
    0.45
     claim
    0.44
    ри
    0.44
    ﺒ
    0.44
     question
    0.43
    Act Density 0.000%

    No Known Activations