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

    Neuronpedia

    INDEX
    Explanations

    "ly" suffix and "newly"

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     системи
    -0.07
    ][:
    -0.07
     Sioux
    -0.07
     sour
    -0.07
     troub
    -0.07
     فيه
    -0.07
    ponde
    -0.07
    .attribute
    -0.07
     май
    -0.07
     آتش
    -0.07
    POSITIVE LOGITS
     newly
    0.13
     Newly
    0.10
    by
    0.07
    .of
    0.07
    700
    0.07
    회의
    0.07
     Wealth
    0.07
    .weapon
    0.07
    最新
    0.06
     formation
    0.06
    Act Density 0.005%

    No Known Activations