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

    Neuronpedia

    INDEX
    Explanations

    male first names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Isso
    0.65
     Z
    0.61
    0.61
     Servicios
    0.60
    <0x80>
    0.60
     organismo
    0.60
     Buena
    0.60
     Instituto
    0.60
     Neue
    0.59
     aumentar
    0.59
    POSITIVE LOGITS
    ův
    0.73
    вЂ
    0.73
     miał
    0.69
    とその
    0.68
    ׳
    0.67
     sightings
    0.66
    ीण
    0.65
    '
    0.64
    ről
    0.64
    ´
    0.63
    Act Density 0.130%

    No Known Activations