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

    Neuronpedia

    INDEX
    Explanations

    bound

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     wildfire
    -0.07
    olesterol
    -0.06
    enerative
    -0.06
    erc
    -0.06
     nie
    -0.06
     overhe
    -0.06
    ittest
    -0.06
     своих
    -0.06
    erre
    -0.06
    '$
    -0.05
    POSITIVE LOGITS
    BOUND
    0.08
     PowerPoint
    0.07
     McKay
    0.07
    
↵
    0.07
     bound
    0.07
     लड़क
    0.07
     motion
    0.07
    bound
    0.07
     outstanding
    0.06
     Bill
    0.06
    Act Density 0.002%

    No Known Activations