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

    Neuronpedia

    INDEX
    Explanations

    stop words

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ождение
    -0.08
    징
    -0.07
     맞
    -0.07
     premieres
    -0.07
     montar
    -0.07
     கை
    -0.07
     monta
    -0.07
     வீ
    -0.07
     참가
    -0.07
     pute
    -0.07
    POSITIVE LOGITS
    念
    0.12
     વિચાર
    0.12
    想着
    0.11
     düşün
    0.11
     minds
    0.11
    -thinking
    0.11
     pensamientos
    0.11
     thoughts
    0.11
    -provoking
    0.11
     aloud
    0.11
    Act Density 0.130%

    No Known Activations