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

    Neuronpedia

    INDEX
    Explanations

    Summary

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     advent
    -0.08
    棒
    -0.08
    Factor
    -0.07
    �
    -0.07
     réparation
    -0.07
    reck
    -0.07
    factor
    -0.07
     punishment
    -0.07
     hobby
    -0.07
    援
    -0.07
    POSITIVE LOGITS
     Executivo
    0.10
     Ejecutivo
    0.09
     summarizes
    0.09
    _summary
    0.09
     resumo
    0.09
    анов
    0.09
     executive
    0.09
    (summary
    0.09
     Executive
    0.09
    Synopsis
    0.09
    Act Density 0.004%

    No Known Activations