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

    Neuronpedia

    INDEX
    Explanations

    programming constructs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ক্ষিতে
    0.26
    郄
    0.24
    獬
    0.24
    িয়াছেন
    0.23
    unción
    0.23
    皞
    0.22
    గ్రహ
    0.22
    avasena
    0.22
    abbati
    0.22
    ຢູ່ໃນ
    0.21
    POSITIVE LOGITS
     and
    0.31
     và
    0.30
    -
    0.30
        
    0.30
     =
    0.29
          
    0.28
     и
    0.28
     &
    0.27
     ,
    0.27
     और
    0.27
    Act Density 0.174%

    No Known Activations