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

    Neuronpedia

    INDEX
    Explanations

    especially

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     অথচ
    0.34
     czyli
    0.30
    ઞ
    0.27
     sondern
    0.27
     и
    0.26
     solutes
    0.26
     και
    0.26
     zodat
    0.26
    ようで
    0.26
    そして
    0.26
    POSITIVE LOGITS
     especially
    0.50
    especially
    0.49
     खासकर
    0.46
     особенно
    0.46
     Especially
    0.46
     خاصة
    0.45
     özellikle
    0.42
     terutama
    0.42
     zejména
    0.41
     especialmente
    0.41
    Act Density 0.008%

    No Known Activations