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

    Neuronpedia

    INDEX
    Explanations

    past participle verbs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    that
    0.52
     Andere
    0.52
    ത്തിലുള്ള
    0.49
    which
    0.48
     swoich
    0.46
     اهمیت
    0.46
     这
    0.44
    ूफ
    0.43
    uchs
    0.42
     שה
    0.42
    POSITIVE LOGITS
     by
    0.90
     with
    0.87
     through
    0.66
     in
    0.63
     from
    0.63
     thru
    0.61
     oleh
    0.61
     dengan
    0.59
     przez
    0.59
     توسط
    0.58
    Act Density 0.073%

    No Known Activations