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

    Neuronpedia

    INDEX
    Explanations

    learning by doing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     belirt
    -0.09
    -0.08
     vanwege
    -0.07
     宁
    -0.07
     apẹrẹ
    -0.07
     RCC
    -0.07
    خيص
    -0.07
    pliance
    -0.07
    ierz
    -0.07
    癌
    -0.07
    POSITIVE LOGITS
    经验
    0.15
     experiencias
    0.14
    経験
    0.14
     experiences
    0.13
     Erfahrungen
    0.13
     경험
    0.13
     firsthand
    0.12
     Experiences
    0.12
     опы
    0.12
     ervaringen
    0.12
    Act Density 0.060%
    No Known Activations