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

    Neuronpedia

    INDEX
    Explanations

    note followed by colon

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     l
    0.46
     menggambarkan
    0.44
     kontroll
    0.43
     দৃঢ়
    0.43
     dà
    0.42
     agonists
    0.40
    described
    0.40
    öder
    0.39
    amalla
    0.39
     যাতে
    0.38
    POSITIVE LOGITS
     notes
    0.85
     Notes
    0.79
    notes
    0.79
    注
    0.79
    Notes
    0.75
     note
    0.73
    Notas
    0.70
    Примечания
    0.69
    Nota
    0.68
     notas
    0.67
    Act Density 0.011%

    No Known Activations