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

    Neuronpedia

    INDEX
    Explanations

    "on" or "ation"

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     kal
    -0.07
     centr
    -0.07
     ira
    -0.06
     inhib
    -0.06
    migration
    -0.06
     erosion
    -0.06
    柱
    -0.06
     approximately
    -0.06
     medi
    -0.06
     crude
    -0.06
    POSITIVE LOGITS
     варианты
    0.11
    .variant
    0.11
     вариант
    0.11
     Variante
    0.10
     variants
    0.10
    玩法
    0.10
     variante
    0.10
     Varianten
    0.10
     variations
    0.10
     вариан
    0.09
    Act Density 0.013%

    No Known Activations