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

    Neuronpedia

    INDEX
    Explanations

    metrics

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    artisan
    -0.08
    arbeit
    -0.08
    ţa
    -0.08
     oste
    -0.07
    /cupertino
    -0.07
    lå
    -0.07
     sequence
    -0.07
     περί
    -0.07
    ța
    -0.07
     renda
    -0.07
    POSITIVE LOGITS
     Monitoring
    0.10
     monitored
    0.10
     monitoring
    0.10
    _monitor
    0.10
     acompanhamento
    0.10
     Monitor
    0.09
    监
    0.09
    Monitoring
    0.09
     measuring
    0.09
     монитор
    0.09
    Act Density 0.001%

    No Known Activations