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

    Neuronpedia

    INDEX
    Explanations

    technical specifications/measurements

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     bait
    -0.07
    swap
    -0.06
     вул
    -0.06
    Cars
    -0.06
    ucursal
    -0.06
     hay
    -0.06
    amarin
    -0.06
     ø
    -0.06
    exist
    -0.06
    .no
    -0.06
    POSITIVE LOGITS
    榜
    0.07
     intermediary
    0.07
     interpre
    0.07
                    
    0.07
     depiction
    0.06
    "))
    0.06
    collections
    0.06
    例
    0.06
     Decomp
    0.06
    327
    0.06
    Act Density 0.025%

    No Known Activations