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

    Neuronpedia

    INDEX
    Explanations

    provide/deliver

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ,:)
    -0.06
    ीर
    -0.06
    (Register
    -0.06
    モデル
    -0.06
     Yorkers
    -0.06
    compiler
    -0.06
    果
    -0.06
     burg
    -0.06
     ou
    -0.06
    �
    -0.06
    POSITIVE LOGITS
    There
    0.06
     Raised
    0.06
    었
    0.06
     Youth
    0.06
     VALUE
    0.06
    šť
    0.06
    declar
    0.06
     gave
    0.06
    flight
    0.06
    .rect
    0.06
    Act Density 0.105%

    No Known Activations