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

    Neuronpedia

    INDEX
    Explanations

    data payload password

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    িয়নের
    0.34
    ၷ
    0.33
     بواسطة
    0.33
     verses
    0.32
     buddhav
    0.32
    反應
    0.31
     reactions
    0.30
     अस्त
    0.30
     REACTIONS
    0.29
     reactant
    0.29
    POSITIVE LOGITS
    мур
    0.29
    писки
    0.27
     saan
    0.27
    Tour
    0.27
    Riley
    0.27
    ly
    0.26
    נו
    0.26
     weekend
    0.25
     trai
    0.25
    цвет
    0.25
    Act Density 22.689%

    No Known Activations