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

    Neuronpedia

    INDEX
    Explanations

    0.00x numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ত্রিম
    0.38
     Theorie
    0.35
    ूथ
    0.35
    Oath
    0.35
    万里
    0.34
    Batter
    0.34
     tangga
    0.34
    窜
    0.34
    难道
    0.34
    Responding
    0.33
    POSITIVE LOGITS
     lakh
    0.45
    yn
    0.43
    is
    0.41
    bert
    0.41
     lod
    0.40
    are
    0.38
    itya
    0.38
    itee
    0.38
    alt
    0.37
     itu
    0.37
    Act Density 0.039%

    No Known Activations