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

    Neuronpedia

    INDEX
    Explanations

    Hollow, Hulu, Hollow Knight

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     তৎপর
    0.38
     Derry
    0.38
    দর
    0.37
     Assert
    0.36
     Terbang
    0.36
    pool
    0.35
     कलेक्टर
    0.35
    bag
    0.35
    zip
    0.35
    Bag
    0.34
    POSITIVE LOGITS
     thủy
    0.41
    semble
    0.38
     stem
    0.38
     खो
    0.38
     stemmed
    0.37
    进化
    0.37
     conceptual
    0.36
    cobra
    0.35
    unic
    0.35
    teen
    0.35
    Act Density 0.021%

    No Known Activations