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

    Neuronpedia

    INDEX
    Explanations

    older

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     PM
    -0.07
    .way
    -0.06
    386
    -0.06
     physicists
    -0.06
     Wig
    -0.06
     AM
    -0.06
    Hard
    -0.06
     работы
    -0.06
     predicted
    -0.06
    emory
    -0.06
    POSITIVE LOGITS
     někter
    0.07
     mapStateToProps
    0.07
    něji
    0.07
     disag
    0.06
    loe
    0.06
    ніверсит
    0.06
     çeşitli
    0.06
    ιών
    0.06
     ierr
    0.06
     وحدة
    0.06
    Act Density 0.016%

    No Known Activations