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

    Neuronpedia

    INDEX
    Explanations

    price or

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     denen
    0.75
    以及
    0.70
     các
    0.66
     주요
    0.64
     உள்ளன
    0.64
     actuales
    0.63
     kojima
    0.63
     voltak
    0.63
     quienes
    0.62
     जिनमें
    0.62
    POSITIVE LOGITS
     или
    1.04
     or
    1.02
     یا
    0.91
     atau
    0.90
    หรือ
    0.88
     someplace
    0.88
     somewhere
    0.86
     thats
    0.85
     someone
    0.85
     vagy
    0.85
    Act Density 1.066%

    No Known Activations