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

    Neuronpedia

    INDEX
    Explanations

    German and English words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    啉
    0.52
    と思います
    0.52
    går
    0.51
    d
    0.48
    can
    0.47
    률
    0.47
    leton
    0.46
    g
    0.46
    たり
    0.46
    das
    0.46
    POSITIVE LOGITS
    omics
    0.71
    vironment
    0.63
     گے
    0.60
    chyma
    0.58
    auts
    0.58
    etics
    0.57
    ‍♂️
    0.56
    strual
    0.54
    uclear
    0.54
    GLISH
    0.54
    Act Density 0.066%

    No Known Activations