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

    Neuronpedia

    INDEX
    Explanations

    optimized maintenance

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     monitors
    0.49
    Nexus
    0.49
     a
    0.47
    casa
    0.44
     себя
    0.44
     مک
    0.43
    ने
    0.42
    Según
    0.42
    δια
    0.41
    𝙿
    0.40
    POSITIVE LOGITS
    ]
    0.46
     เรา
    0.45
    ಗ್ಗ
    0.43
     Nachricht
    0.42
     Notify
    0.42
    િલ
    0.41
    ],
    0.41
    anns
    0.41
    });
    0.41
     உயர்ந்த
    0.40
    Act Density 0.001%

    No Known Activations