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

    Neuronpedia

    INDEX
    Explanations

    if(!require

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     title
    0.40
     पृ
    0.37
    Spec
    0.36
    title
    0.36
     شروع
    0.36
     Doi
    0.35
     index
    0.35
     koron
    0.35
     Spec
    0.35
     bắt
    0.35
    POSITIVE LOGITS
    Defocused
    0.46
     Beasley
    0.43
    osters
    0.43
     lamented
    0.41
     beverage
    0.41
    def
    0.41
     ক্যাথ
    0.40
     beverages
    0.40
     def
    0.40
     bicyclists
    0.38
    Act Density 0.000%

    No Known Activations