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

    Neuronpedia

    INDEX
    Explanations

    maximizing or minimizing outcomes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ia
    0.31
    is
    0.30
    neath
    0.30
    sm
    0.29
    heses
    0.29
    más
    0.29
    的基础上
    0.29
    structure
    0.28
    с
    0.28
    sp
    0.28
    POSITIVE LOGITS
     faptul
    0.33
     quanto
    0.32
    ي
    0.32
    ت
    0.32
     roky
    0.31
     outubro
    0.30
     Ihre
    0.30
    อกาส
    0.29
     cuánto
    0.29
    يرا
    0.29
    Act Density 0.140%

    No Known Activations