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

    Neuronpedia

    INDEX
    Explanations

    alone together

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    िस्थित
    0.43
    ódio
    0.43
     રહે
    0.42
    Antaeotricha
    0.40
    логов
    0.40
     género
    0.40
     lanza
    0.39
     lanz
    0.39
     mobilize
    0.39
    Kurt
    0.39
    POSITIVE LOGITS
    techniques
    0.48
    canvas
    0.44
     Canvas
    0.44
    dock
    0.44
    تها
    0.42
    extra
    0.42
    events
    0.42
     सचिवा
    0.41
    čki
    0.40
    yside
    0.40
    Act Density 0.002%

    No Known Activations