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

    Neuronpedia

    INDEX
    Explanations

    shift in X

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ite
    1.49
    led
    1.49
    ne
    1.41
    are
    1.35
    eli
    1.29
    ase
    1.27
    re
    1.26
    its
    1.23
    eres
    1.23
    ade
    1.19
    POSITIVE LOGITS
     przyję
    1.52
     shift
    1.37
    シフト
    1.31
    くちゃ
    1.27
    ⦖
    1.26
     planis
    1.17
     mít
    1.16
     uczni
    1.16
     valoración
    1.16
     Consultado
    1.15
    Act Density 0.019%

    No Known Activations