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

    Neuronpedia

    INDEX
    Explanations

    group theory

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     являются
    -0.07
    ивания
    -0.07
     alo
    -0.07
     resistance
    -0.06
     QLineEdit
    -0.06
     мон
    -0.06
    NG
    -0.06
    ملة
    -0.06
     Midwest
    -0.06
    通り
    -0.06
    POSITIVE LOGITS
     implicated
    0.07
    gricult
    0.06
     NGO
    0.06
    tweet
    0.06
    ~":"
    0.06
     ingin
    0.06
     timely
    0.06
     ATS
    0.06
     blaze
    0.06
    encrypt
    0.06
    Act Density 0.024%

    No Known Activations