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

    Neuronpedia

    INDEX
    Explanations

    need to adapt or expect

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ණ්
    0.44
     meestal
    0.44
     impossibile
    0.43
     моя
    0.43
     mijn
    0.42
     María
    0.42
     poiché
    0.41
    數字
    0.41
    ᱕
    0.41
     மிகப்பெரிய
    0.40
    POSITIVE LOGITS
     придется
    0.47
     CGPoint
    0.41
    ที่จะ
    0.41
     graduates
    0.40
     &
    0.40
     constrain
    0.39
    薏
    0.39
     taper
    0.38
     glVertex
    0.38
    ancies
    0.38
    Act Density 0.006%

    No Known Activations