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

    Neuronpedia

    INDEX
    Explanations

    enhancements

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Document
    -0.07
     Дем
    -0.07
     Shore
    -0.07
     Santa
    -0.07
    isNaN
    -0.06
     Study
    -0.06
    اش
    -0.06
    Mission
    -0.06
    cipher
    -0.06
    Essay
    -0.06
    POSITIVE LOGITS
    rief
    0.07
     gratuita
    0.07
    ▍▍▍▍▍▍▍▍▍▍▍▍▍▍▍▍
    0.06
     perfected
    0.06
     bitir
    0.06
     졸업
    0.06
     měsí
    0.06
    روت
    0.06
     cough
    0.06
    “你
    0.06
    Act Density 0.108%

    No Known Activations