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

    Neuronpedia

    INDEX
    Explanations

    magnet

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Teknik
    -0.07
     dịch
    -0.07
    ivní
    -0.06
     ninth
    -0.06
     esa
    -0.06
    SqlCommand
    -0.06
     KW
    -0.06
     лік
    -0.06
    ission
    -0.06
     ож
    -0.06
    POSITIVE LOGITS
     magnet
    0.15
     Magnet
    0.12
     Democrat
    0.09
    agnet
    0.08
    (dot
    0.08
     magnets
    0.08
    Planet
    0.07
    ter
    0.07
     sat
    0.07
    dot
    0.07
    Act Density 0.003%

    No Known Activations