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

    Neuronpedia

    INDEX
    Explanations

    analyze critical chain

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ب
    0.59
    aniline
    0.51
     volatiles
    0.50
    溽
    0.50
    ıları
    0.49
    નગર
    0.49
    و
    0.49
    imcoords
    0.49
     manglid
    0.49
    秏
    0.48
    POSITIVE LOGITS
     mince
    0.41
    खी
    0.40
     cause
    0.40
     commencer
    0.39
     Jetzt
    0.39
    Jetzt
    0.38
     dyr
    0.38
     can
    0.37
     rep
    0.37
    いますが
    0.37
    Act Density 0.004%

    No Known Activations