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

    Neuronpedia

    INDEX
    Explanations

    specific measurements or categories

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ilent
    0.44
    ,":
    0.39
    ައް
    0.39
    任務
    0.39
     منك
    0.39
     તેણીએ
    0.38
    .'</
    0.37
    EXEC
    0.36
    ற்க
    0.36
    ँकि
    0.36
    POSITIVE LOGITS
     ఎంత
    0.44
     gross
    0.43
     Switch
    0.43
     Publication
    0.43
     switch
    0.41
     Graph
    0.40
     нюан
    0.40
     Graphic
    0.39
    GraphQl
    0.39
     сексуа
    0.39
    Act Density 0.000%

    No Known Activations