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

    Neuronpedia

    INDEX
    Explanations

    descriptions of mechanisms and definitions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ەن
    0.41
    谗
    0.37
     ترین
    0.37
     phon
    0.37
     canale
    0.37
    蝴
    0.37
    روت
    0.37
     gneiss
    0.36
     خ
    0.36
     சேன
    0.35
    POSITIVE LOGITS
    你有
    0.46
     you
    0.42
     just
    0.39
     evaluate
    0.39
     find
    0.38
     bring
    0.38
    compass
    0.38
    adur
    0.38
     Lovely
    0.38
     জিয়া
    0.38
    Act Density 0.000%

    No Known Activations